dad: A Pathfinder

This is a computer-generated pathfinder created against the Distant Reader study called dad.

Each Distant Reader study carrel is composed of many individual items. Each item is bibliographically described with author, title, date, summary, and keyword values. Below is a list of the items' most signficant keywords as well as lists of the items themselves. Purpusing the content of this pathfinder provides the student, researcher, or scholar with one way to get their heads around the scope of the carrel. The keywords include:

Language; Dialogue; Information; Relations; Corpus; Data; Example; Model; Speech; System; Text; Analysis; Participants; Sentence; Processing; Speaker; Type; State; Use; Relation

Depending on how this pathfinder was created, many of the bibliographic sections will include elaborations on the meaning(s) of the given keywords. These elaborations were generated by feeding the items' summaries to a large langauge model and asking the model to address the question, "What is X?", where "X" is the keyword. The result will be a few sentences of elaboration. Be forewarned. The elaborations are often plausible, but they should not be take as truth. Instead, they should be taken as points for consideration.

• Exploring "Associative Talk": When German Mothers Instruct Their Two Year Olds about Spatial Tasks by Rohlfing, Katharina J. (2011) - Children's task performance correlated significantly with reported productive spatial lexicon (r = .52, df = 19, p < .03) but not with the reported receptive spatial lexicon (r = .28), suggesting that a more advanced reported productive spatial lexicon helped children to solve the task successfully. The relations ON and UNDER were chosen because of the different level of knowledge children demonstrate in understanding them: Whereas the preposition ON is reported to be understood very early, the understanding of UNDER is relatively poor at the age of 20 to 24 months (for example, Clark, 1973; Rohlfing, 2005). Keywords: attention; bring; canonical; children; development; discourse; events; example; follow; language; mothers; relation; strategies; task
• Concept Type Prediction and Responsive Adaptation in a Dialogue System by Stoyanchev, Svetlana; Stent, Amanda J. (2012) - Table 5 shows a confusion matrix for confir- mation prompt concept type and post-confirmation utterance concept type. Manual approach: We manually selected five lexical features: yes (indicates a confirma- tion), no (indicates a rejection), to and from (indicate presence of concept types place and time), and I (indicates a complete sentence). Keywords: bus; concept; concept type; confirm; confirmation; dialogue; features; language; lex; model; pass; place; raw; recognition; speech; speech recognition; system; time; type; user; utterances
• Non-Native Differences in Prosodic-Construction Use by Ward, Nigel G. ; Gallardo, Paola (2017) - For example, Zimmerer’s measurements showed that non-native speakers use much less pitch variation (Zimmerer et al., 2014). Because we are centrally interested in what people actually do in conversation, we wish to discover from the data itself what functions are expressed with prosody, and how non-native speakers differ. Keywords: constructions; data; dialog; differences; dimension; english; example; features; functions; intonation; language; native; non; pitch; prosodic; prosody; reference; spanish; speakers; speech; turn; use; ward
• Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus by Lowe, Ryan ; Pow, Nissan ; Serban, Iulian Vlad ; Charlin, Laurent ; Liu, Chia-Wei ; Pineau, Joelle (2017) - In order to be able to correctly answer questions regarding Ubuntu and solve the user’s problem, dialogue models will inevitably require some knowledge of the Ubuntu domain. Classification dialogue models can make errors due to an inability to detect semantic similarities between sentences, or due to the detection of spurious similarities. Keywords: context; conversation; corpus; dialogue; dialogue corpus; dialogue systems; encoder; end; end dialogue; eou; et al; figure; language; lstm; metrics; model; proceedings; response; rnn; set; systems; task; training; ubuntu; user; utterance; word
• A Psycholinguistic Model for the Marking of Discourse Relations by Yung, Frances ; Duh, Kevin ; Komura, Taku ; Matsumoto, Yuji (2017) - The probability is estimated by counting the co-occurrences in the PDTB in which explicit and implicit DCs are labeled with discourse relation senses. The aim of the experiment is to answer our research questions introduced in the end of Section 2. 4.1 Data and setting The experiment is based on the annotation of discourse relation senses and explicit/implicit DCs in the PDTB, as described in Section 2.1. Keywords: arguments; dcs; discourse; discourse relations; implicit; information; informativeness; language; listener; marking; model; pages; pdtb; proceedings; production; relation; sense; speaker; use; utterance
• Towards Integration of Cognitive Models in Dialogue Management: Designing the Virtual Negotiation Coach Application by Malchanau, Andrei ; Petukhova, Volha ; Bunt, Harry (2019) - We provide an overview of existing approaches and systems for cognitive tutoring tasks, as well as dialogue systems used in negotiation domains. MALCHANAU, PETUKHOVA AND BUNT Technique Example task Dialogue phenomena handled Finite state script Long-distance calling User answers questions Frame based Getting train arrival and departure information User asks questions, simple clarifications by the system Information State Update Travel booking agent Flexible shifts between pre-determined topics/tasks Refined grounding mechanisms Plan based Kitchen design consultant Dynamically generated topic structures, e.g. negotiation dialogues Agent based Disaster relief management Different modalities, e.g. planned world and actual world Collaborative planning and acting Probabilistic approaches Various information-seeking tasks, Dialogue policies design, i.e. learning negotiation games combined with the most approaches mentioned above Chat-oriented; Retail ‘chat commerce’ Question-answering skills interactive pattern matching Psychotherapies, personal assistant Social interactive aspects /template-based Table 1: State-of-the-art techniques for task-oriented dialogue system. Keywords: actions; acts; agent; behaviour; bunt; cognitive; context; cooperative; data; dialogue; dialogue act; dialogue management; dialogue manager; dialogue system; et al; evaluation; feedback; human; information; instance; interaction; issue; language; learning; malchanau; management; manager; models; negotiation; offer; pages; participants; partner; performance; petukhova; preferences; proceedings; processing; speech; state; strategies; strategy; system; task; tutoring; user; value
• Reinforcement adaptation of an attention-based neural natural language generator for spoken dialogue systems by Riou, Matthieu ; Jabaian, Bassam ; Huet, Stéphane ; Lefèvre, Fabrice (2019) - This approach has been used previously in dialogue systems for language understanding (Ferreira et al., 2015, 2016). Rank Initial system Adapted system 1 111 (22.0%) 143 (28.5%) 2 51 (10.2%) 103 (20.6%) 3 18 (3.6%) 75 (15.0%) Keywords: attention; bandit; cost; data; dialogue; generation; initial; language; learning; lstm; model; system; user; utterance
• A Narrative Sentence Planner and Structurer for Domain Independent, Parameterizable Storytelling by Lukin, Stephanie M. ; Walker, Marilyn A. (2019) - or How to Generate Stories with Surprise Endings by Exploiting the Disparity of Knowledge between a Story’s Reader and its Characters. Despite control over the story generation, these systems place less priority on the realization of the texts, and are instead typically use pre-authored pieces of story text or templates. Keywords: baseline; bowl; character; content; crow; deck; discourse; fabula; fox; generation; language; narrative; narrative sentence; narrator; order; pages; person; planner; point; proc; realization; scheherazade; sentence; sig; speech; squirrel; stories; story; storytelling; structurer; table; text; variations; voice; walker; work
• Introduction to the Special Issue on Incremental Processing in Dialogue by Rieser, Hannes; Schlangen, David (2011) - David DeVault, Kenji Sagae and David Traum present in the paper Interpretation and Prediction of Utterance Meaning for Interactive Dialogue techniques for building one such module for incremental dialogue systems, namely for the component that does interpretation. Baumann et al.’s specification of an evaluation framework should prove a valuable general contribution to the growing field of incremental spoken dialogue systems. Keywords: bielefeld; david; dialogue; incremental; incrementality; language; model; poesio; processing; research; rieser; schlangen; university
• Talking in another person’s shoes: Incremental perspective-taking in language processing by Brown-Schmidt, Sarah; Hanna, Joy E. (2011) - This design would be expected to produce weak common ground effects as it is well known that overhearers do not form common ground in the same way as full participants (Schober & Clark, 1989; also see Wilkes-Gibbs & Clark, 1992). A processing mechanism that focused attention on common ground information prior to each linguistic act would frequently make the wrong prediction. Keywords: brown; constraint; effects; et al; ground; hanna; information; interpretation; journal; keysar; language; memory; michael; participants; perspective; processing; role; schmidt; taking; tanenhaus; use
• Incrementality and the Dynamics of Routines in Dialogue by Gargett, Andrew (2011) - For this formalisation of dual processing, we extend the lexical architecture of DS, so that lexical entries incorporate both the usual DS lexical actions, but also include the output semantic structures which result from employing such lexical actions. Our dual processing account of lexical architecture models lexical nodes as consisting not only of strings and lexical actions for computing representations, but also stored semantic structure. Keywords: account; actions; context; dialogue; information; language; model; modelling; nodes; processing; routines; routinisation; structure; tree; ty(e; update
• Incrementality and intention-recognition in utterance processing by Gregoromichelaki, Eleni; Kempson, Ruth; Purver, Matthew; Mills, Gregory J. ; Cann, Ronnie; Meyer-Viol, Wilfried; Healey, Patrick G. T. (2011) - In contrast then to Bratman’s account of intentional action whichsees the planning struc- tures involved as distinctive of rational agents, distinguishing them from entities exhibiting merely purposive behaviour (see e.g. Bratman, 1999, 5), in Millikan’s naturalistic perspective, function, i.e. meaning, does not depend upon speaker intentions. Similarly, hearers under- stand speech through direct perception of what the speech is about without necessary reflection on speaker intentions. Keywords: account; cann; communication; construction; context; coordination; dialogue; grammar; gregoromichelaki; gricean; healey; hearer; incrementality; intention; kempson; language; level; mechanisms; model; order; participants; processing; purver; recognition; speaker; tree; utterance; view
• An Incremental Model of Anaphora and Reference Resolution Based on Resource Situations by Poesio, Massimo; Rieser, Hannes (2011) - (13) [ uDet, uNP , uN ′ | uNP :NP XXXXXX ������ uDet:Det the:λPλP ′[y|y is ιxP (x)];P ′(y) uN ′ :N’ ] 3.4 The Ingredients of Incrementality, II: Defeasible Reasoning The evidence on incremental interpretation and parallel hypothesis generation discussed in section 2 suggests that utterance interpretation is a form of defeasible inference in which competing hypothe- ses are activated, one of which is rapidly selected, whereas the other ones are discarded (Poesio 1994, 1995a,b, To Appear). Although we only propose here this treatment for surface anaphors, we suspect a similar DD-MATCH rule may generate anaphoric interpretation hypotheses for definite descriptions on the basis of head similarity. Keywords: account; anaphora; anaphoric; default; discourse; et al; information; interpretation; language; object; poesio; ptt; reference; resolution; resource; rieser; section; semantics; situation; theory; unp; utterance; ′(y
• Varieties of Question Generation: Introduction to this Special Issue: Introduction to this Special Issue by Piwek, Paul ; Boyer, Kristy Elizabeth (2012) - Microsoft Word Template Dialogue and Discourse 3(2) (2012) 1˗9 doi: 0.5087/dad.2012.201 ©2012 Paul Piwek and Kristy Boyer Varieties of Question Generation: Introduction to this Special Issue Paul Piwek P.PIWEK@OPEN.AC.UK Centre for Research in Computing The Open University Walton Hall Milton Keynes, MK7 6AA, United Kingdom Kristy Elizabeth Boyer KEBOYER@NCSU.EDU Department of Computer Science North Carolina State University 890 Oval Dr. Campus Box 8206, Raleigh, NC 27695-8206, United States Introduction Questions are a topic that is ideally placed at the intersection of research on dialogue and discourse: in most dialogue, questions are the driving force, setting its direction, whereas answers to questions require discourse processing (e.g., contextual resolution in the case of short answers) or can be viewed as a piece of discourse themselves (e.g., an explanation in response to a why- question). In contrast with Formal/Computational Semantics and Natural Language Processing, Question Generation has a substantial history in Education and Psychology, see Olney et al. Keywords: dialogue; generation; input; issue; language; output; question; question generation; representation; research; text
• Semantics-based Question Generation and Implementation by Yao, Xuchen ; Bouma, Gosse ; Zhang, Yi (2012) - The task of question generation contains multiple subareas. When people perform question generation, a transformation from declarative sentences to in- terrogatives happens. Keywords: arg1; cat; clause; eps; evaluation; figure; generation; grammar; language; model; monday; mrs; mrsqg; neq; question; question generation; rstr; semantics; sentences; system; transformation; wedding
• Question Generation for French: Collating Parsers and Paraphrasing Questions by Bernhard, Delphine ; Viron, Louis de ; Moriceau, Véronique ; Tannier, Xavier (2012) - How do system questions influence lexical choices in user answers. Our goal in doing so is to evaluate the impact of the prior analysis tools on the quality and quantity of generated questions. Keywords: analysis; answer; answering; bernhard; clef; eng; evaluation; french; generation; information; john; language; moriceau; names; noun; pages; proceedings; question; question generation; sentence; simplification; source; subject; system; verb
• A Detailed Account of The First Question Generation Shared Task Evaluation Challenge by Rus, Vasile ; Wyse, Brendan ; Piwek, Paul; Lintean, Mihai ; Stoyanchev, Svetlana ; Moldovan, Cristian (2012) - The last step, question construction, is about realizing the question given the selected content, question type, and the context in which the question is being asked. Question types (who/what/why/…) generated for each paragraph should be diverse, i.e. different question types are preferred in the set of 6 required questions. Keywords: answers; criteria; evaluation; input; language; paragraph; participants; question; question generation; question type; results; scores; sentence; stec; systems; table; task; text
• A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version by Serban, Iulian Vlad ; Lowe, Ryan ; Henderson, Peter ; Charlin, Laurent ; Pineau, Joelle (2018) - In the area of dialogue systems, the trend is less obvious, and most practical systems are still built through significant engineering and expert knowledge. To facilitate research in this area, we have carried out a wide survey of publicly available datasets suitable for data-driven learning of dialogue systems. Keywords: building; conference; conversations; corpora; corpus; data; dataset; dialogue; dialogue corpus; dialogue state; dialogue systems; end; english; et al; evaluation; generation; goal; henderson; human; information; interactions; international; knowledge; language; learning; linguistics; lowe; machine; models; movie; pages; pineau; processing; response; serban; serban et; speech; spoken; state; survey; topics; tracking; understanding; user; words; written; young
• Wait Signals Predict Sarcasm in Online Debates by D’Arcey, J. Trevor; Oraby, Shereen ; Tree, Jean E. Fox (2019) - But written sarcasm does have textual cues that are not available for spoken sarcasm, such as exclamation points and question marks, laughter expressions like lol, emoticons like :), and quotation marks, all of which contribute to irony detection (Carvalho, Sarmento, Silva, & De Oliveira, 2009; this study was done in Portuguese). Contextual cues and regional differences may influence generation and perception of spoken sarcasm as well: common ground between interlocutors led to more sarcasm (Caucci & Kreuz, 2002; Clark, 1996), and Southern U.S. participants’ viewed sarcasm as more hurtful (Dress et al., 2008). Keywords: corpora; corpus; fillers; fox; language; post; response; sarcasm; signals; spoken; tree; wait; words; workers; writing; written
• Visual attention-capture cue in depicted scenes fails to modulate online sentence processing by Burmester, Juliane ; Spalek, Katharina ; Wartenburger, Isabell (2019) - 4.1 Null effect of visual cue on sentence-initial processing Against the background of previous research investigating the interaction of visual cues with linguistic processing, we discuss the absent cue effect of the present study 1) with respect to different aspects of informativity of the visual scene for the comprehension process, and 2) with respect to the different impact of visual cue types (implicit vs. explicit) on sentence comprehension and production. If and when visual cues are integrated into the mental meaning representation of the communicative setting, is still unclear. Keywords: attention; burmester; comprehension; cue; cues; discourse; information; language; linguistic; order; processing; referent; roi; sentence; sentence processing; study; time; topic; word
• Incremental sentence production inhibits clausal coordinate ellipsis: A treebank study into Dutch and German by Harbusch, Karin (2011) - She only reports one number dealing with CCE types: 83 sentences embodying SGF, i.e., about 1 percent. We adopt the following PSYCHOLINGUISTICALLY MOTIVATED definitions of CCE types. Keywords: bcr; cce; clausal; clause; conjunct; coordinate; coordination; dutch; edges; ellipsis; example; gapping; german; language; production; section; sentence; spoken; subject; treebank; types; verbmobil
• Are We There Yet?: The Development of a Corpus Annotated for Social Acts in Multilingual Online Discourse by Morgan, Jonathan T. ; Oxley, Meghan ; Bender, Emily M. ; Zhu, Liyi ; Gracheva, Varya ; Zachry, Mark (2013) - See Table 3 for a breakdown of authority claim annotation across the three languages, and Table 4 for a breakdown of alignment move annotation in English. For example, Hypothesis (ii) below is based on recurring observations by annotators that Mandarin Wikipedia editors tended to not use any explicit negators, but instead used paired conjunctions to indicate the negation. Keywords: acts; agreement; alignment; alignment moves; annotation; annotators; authority; authority claims; claims; data; discussions; editors; english; guidelines; language; mandarin; moves; pages; participants; russian; total; turns; types; wikipedia; work
• Annotating the meaning of discourse connectives by looking at their translation: The translation-spotting technique by Cartoni, Bruno ; Zufferey, Sandrine ; Meyer, Thomas (2013) - In order to disambiguate discourse connectives for machine translation (and more specifically for statistical machine translation (SMT), the COMTIS project proposes to pre-process their occurrences and label them with meaning tags, thus enabling the SMT system to make the correct choice in the target language. Published online 04/13 Annotating the Meaning of Discourse Connectives by Looking at their Translation: The Translation Spotting Technique Bruno Cartoni BRUNO.CARTONI@UNIGE.CH Département de Linguistique Université de Genève Rue de Candolle 2 CH-1211 Genève 4 Sandrine Zufferey S.I.ZUFFEREY@UU.NL Utrecht Institute of Linguistics Trans 10 NL-3512 JK Utrecht Thomas Meyer THOMAS.MEYER@IDIAP.CH Idiap Research Institute Centre du Parc Rue Marconi 19 CH-1920 Martigny Editors: Stefanie Dipper, Heike Zinsmeister, Bonnie Webber Abstract The various meanings of discourse connectives like while and however are difficult to identify and annotate, even for trained human annotators. Keywords: alors; annotation; annotators; cases; connectives; contrast; data; discourse; english; french; language; meaning; même; que; relations; sense; spotting; translation
• Turkish Discourse Bank: Porting a discourse annotation style to a morphologically rich language by Zeyrek, Deniz ; Demirşahin, Işın ; Çallı, Ayışığı B. Sevdik (2013) - TURKISH DISCOURSE BANK 175 and takes discourse connectives as discourse-level predicates with a binary argument structure (Prasad et al., 2007). In creating a bank of discourse based on connectives, we do not claim that discourse connectives are the only means establishing coherence; we merely take them as the basic elements of discourse which make coherence relations salient. Keywords: agreement; annotation; annotators; arg2; arguments; bank; connectives; discourse; language; subordinators; tdb; turkish
• Annotation of negotiation processes in joint-action dialogues by Tenbrink, Thora ; Eberhard, Kathleen ; Shi, Hui ; K ̈ubler, Sandra ; Scheutz, Matthias (2013) - Our focus in this paper is on annotation schemes that capture structures of negotiation processes in joint action dialogues, building on speech-act related theories (e.g., Allen and Perrault, 1980; Co- hen and Levesque, 1980) to describe dialogic actions in discourse (i.e., dialogue acts as specialized speech acts referring to dialogue actions). We conclude by a brief discussion of the challenges ahead and consequences for dialogue annotation and corpus data collection. Keywords: action; annotation; assert; corpus; d311; dialogue; director; example; gestures; ground; human; information; interaction; intonation; language; map; matcher; negotiation; participants; request; scheme; structure; system; table; task; tenbrink; updating; user; utterance
• On Temporality in Discourse Annotation: Theoretical and Practical Considerations by Evers-Vermeul, Jacqueline ; Hoek, Jet ; Scholman, Merel C.J. (2017) - An important difference between causal vs. additive relations and causal vs. temporal relations is that not all causal relations are temporal, and that during the annotation process one would therefore want to be able to attribute these values simultaneously in order to be able to distinguish between temporal causal relations and non-temporal causal relations. This means that temporal relations meet the requirements set by the Cognitive approach of Coherence Relations (CCR) to be considered coherence relations, and that CCR would need a way to distinguish temporal relations within its annotation system. Keywords: additive; annotation; causal; ccr; coherence; coherence relations; connectives; dimension; discourse; events; language; markers; order; relations; sanders; segments; temporal; temporality; time
• Dialog Structure Through the Lens of Gender, Gender Environment, and Power by Prabhakaran, Vinodkumar ; Rambow, Owen (2017) - We expect the SVM-based supervised learning system using quadratic kernel to capture the interdependence between dialog structure features and gender features that we found in our statistical analysis presented in Section 6 and Section 7. This reduction of 2.4% percentage points in accuracy shows that gender features are in fact useful for this power prediction task. Keywords: corpus; dialog; discourse; email; environments; features; gender; gender environment; language; male; messages; participants; power; prabhakaran; structure; subordinates; superiors; thread; use
• An Empirical Analysis of Subjectivity and Narrative Levels in Weblog Storytelling Across Cultures by Swanson, Reid ; Gordon, Andrew S. ; Khooshabeh, Peter ; Sagae, Kenji ; Huskey, Richard ; Mangus, Michael ; Amir, Ori ; Weber, Rene (2017) - Personal stories found on Weblogs share many of the fundamental properties of the other types of discourse in this genre, but are widely available on the web across many different cultures. In our first experiment we investigate this question through an empirical study that compares the distribution of narrative clauses across three different cultures over a large number of personal stories found on the Web. Keywords: analysis; chinese; clauses; cultures; diegetic; discourse; distribution; events; example; gordon; language; levels; narrative; narrator; participants; reader; stories; story; subjectivity; types
• Discourse Markers in Speech: Distinctive Features and Corpus Annotation by Crible, Ludivine ; Cuenca, Maria-Josep (2017) - Besides examples and some corpus-based quantitative findings of the distribution of these features, the paper also provides a review of how existing writing-based frameworks handle (or not) the particular characteristics of spoken DMs. In the following sections, some characteristics of spoken DMs will be discussed and illustrated by naturally-occurring examples taken from DisFrEn, a French-English comparable corpus fully annotated for discourse markers (Crible, 2017b). Keywords: annotation; corpus; discourse; discourse markers; dms; functions; language; markers; pages; pdtb; relations; scope; speech; texts; topic; use; writing; written
• From Discursive Practice to Logic? Remarks on Logical Expressivism by Kibble, Rodger (2020) - 3.2 Summary To summarise: in this section we have considered various examples which appear to challenge the notion that logical connectives can be extracted from natural language practice by identifying in- variant uses under substitution of the accompanying non-logical vocabulary, owing to the pervasive influence of linguistic and non-linguistic context on the behaviour of lexical items including even “logical” terms. Introduction This paper combines a critical appraisal of Robert Brandom’s notion of discursive practice and in particular his programme of logical expressivism with a novel conjectural account of the genesis of the conditional locution. Keywords: account; agent; bourdieu; brandom; commitment; conditional; dialogue; discourse; example; inference; kibble; language; logic; material; paper; practice; semantics; speaker; terms; theory; vocabulary; work
• Opinion Piece: How People Structure Representations of Discourse by Garnham , Alan (2021) - Situation model theory does not specify what relations allow eventualities to be linked via indices. Space has been particularly important in the history of situation model theory, largely because it was in spatial domains that it was easiest to show that situation models had different structures from the sentences describing them (Potts, 1974, and many subsequent papers). Keywords: characters; comprehension; discourse; events; eventualities; example; garnham; idea; language; models; narrative; people; person; protagonists; psychology; relations; representations; situation; story; structure; text; theory; types
• Please, Please, Just Tell Me: The Linguistic Features of Humorous Deception by Skalicky, Stephen; Duran, Nicholas; Crossley, Scott A (2020) - This may suggest that deceptive BTL stories are therefore more specific or detailed in some regards when compared to the truthful BTL news stories. The fictional narratives that comprise deceptive BTL stories, however, may lack this level of coherence because they rely more heavily on invented situations. Keywords: analysis; btl; btl stories; deception; features; humor; language; model; news; number; radio; stories; story; text; variables; words
• GailBot: An automatic transcription system for Conversation Analysis by Umair, Muhammad; Mertens, Julia Beret; Albert, Saul; de Ruiter, J. P. (2022) - In the Performance section, we compare GailBot transcripts to manual transcripts and those used by Moore (2015), provide an estimate of the transcription time saved by using GailBot, and compare it to existing data annotation systems. In this paper, we use two types of WERs: a strict WER (SWER) and a relaxed WER (RWER), both computed by manually comparing GailBot transcripts to human- produced transcripts. Keywords: analysis; audio; conversation; data; doi; errors; excerpt; features; gailbot; language; line; manual; overlap; plugins; rate; silence; sp1; sp2; speaker; speech; stt; systems; time; transcription; transcripts; turn; word
• Lexical and contextual cue effects in discourse expectations: Experimenting with German 'zwar...aber' and English 'true/sure...but' by Schwab, Juliane; Liu, Mingya (2020) - In particular, we used a self-paced reading task with subsequent naturalness ratings to answer two questions: First, do discourse cues generate an expectation that facilitates processing the dis- course connective (e.g. but), as indexed by reduced reading times? Our study thus provides evidence that the joint presence of discourse cues from multiple linguistic sources can act as cumulative facilitators of discourse processing. Keywords: aber; argument; connective; cue; cues; data; discourse; doi; effects; english; expectations; experiment; frequency; german; gerne; items; language; likes; participants; processing; reading; relation; results; room; sentence; sie; study; times; treadmill; zwar
• When to Say What and How: Adapting the Elaborateness and Indirectness of Spoken Dialogue Systems by Miehle, Juliana; Minker, Wolfgang; Ultes, Stefan (2022) - Analysing the correlation between user and system communication style in human-computer interaction on a multi-lingual data set 4. In Section 4, the corpus used in this work is described and the correlation between user and system communication style is investigated. Keywords: adaptation; classes; classification; communication style; computer; dialogue; dialogue system; elaborateness; et al; features; human; indirectness; interaction; language; miehle; pages; personality; results; speaker; speech; styles; system; table; uar; user; user communication; utterance
• Automatic Essay Scoring Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses by Kumar, Yaman; Parekh, Swapnil; Singh, Somesh; Li, Junyi Jessy; Shah, Rajiv Ratn; Chen, Changyou (2023) - While previous studies indicate that scoring models can be easily fooled, in this paper, we explore the reason be- hind their surprising adversarial brittleness. 4 shows that scoring models do not have the ability to check such common sense. Keywords: aes; association; attributions; bert; chen; conference; doi; essay; essay scoring; et al; language; learning; linguistics; mann; models; oversensitivity; overstability; proceedings; prompt; results; samples; scores; scoring; shah; singla; skipflow; systems; testing; triggers; words
• Bullshit, Pragmatic Deception, and Natural Language Processing by Deck, Oliver (2023) - The next chapter will discuss some limitations and caveats of this detailed annotation process for bullshit examples. This paper aims to introduce bullshitology into the field of NLP by tying it to questions in a QUD-based definition, providing two approaches to bullshit annotation, and finally outlining which combinations of NLP methods will be helpful to classify which kinds of linguistic bullshit. Keywords: analysis; annotation; answer; bullshit; bullshitting; deception; definition; detection; discourse; doi; et al; example; fallis; frankfurt; issn; language; linguistics; methods; nlp; node; pages; proceedings; qud; question; research; shift; shifting; speaker; stokke; truth; url; yes
• The Conversational Discourse Unit: Identification and Its Role in Conversational Turn-taking Management by Hu, Junfei; Degand, Liesbeth (2023) - Following the training, an inter-coder reliability check was performed for 25% (28 minutes) of the conversations, yielding Cohen kappa’s reliability scores of 0.84 for turn-taking identification, 0.91 for the identification of syntactic units and 0.94 for pragmatic units, indicating almost perfect agreement for turn-taking annotation and the identification of syntactic and pragmatic units (Landis & Koch, 1977). Keywords: Discourse segmentation, discourse unit, corpus analysis, pragmatic unit, turn-taking 1 Introduction The linear unfolding of (spontaneous) speech results from a combination of different cognitive encoding and decoding processes (e.g. Auer, 2005; Clark, 1996; Pickering & Garrod, 2021). Keywords: action; analysis; boundaries; boundary; cdu; conversation; cup; degand; discourse; discourse unit; identification; information; intonation; language; pages; pragmatics; prosodic; prosody; role; segmentation; speaker; study; syntax; taking; transition; turn; type; unit
• Self-Repair in Tigrinya: Trouble Sources, Mechanisms and Solutions by Mache Asgede, Dagnew (2024) - Keywords: Tigrinya, self-repair, trouble sources, repair mechanisms, repair solutions 1 Introduction Linguistic repair refers to addressing any language-related concerns during the development of oral discourse. The third section presents and analyzes the data, focusing on trouble sources, repair mechanisms, and the results of self-repair. Keywords: agreement; analysis; asgede; constituent; conversation; cut; data; discourse; example; foc; ipv; language; markers; mean; mechanisms; participants; repair; segment; self; sources; speaker; speech; table; tigrinya; trouble; turn; utterance; word; ʔɨbba
• Digging Communicative Intentions: The Case of Crises Events by Benamara, Farah; Mari , Alda; Meunier, Romain; Moriceau, Véronique; Moudjari, Leila; Tinarrage, Valentin (2024) - Detecting urgency status of crisis tweets: A transfer learning approach for low resource languages. In particular, we explore the correlations between SA vs. urgency, SA vs. intention to act categories as well as SA vs. the types of crises for both levels of SA annotations. Keywords: acts; analysis; annotations; assertive; categories; classification; conference; content; crisis; dataset; detection; distribution; et al; events; french; information; intentions; interrogative; jussive; label; language; level; linguistics; mari; media; messages; multi; pages; proceedings; results; sa1; sa2; speech; sub; table; tweet; urgency; urgent; url; vs.
• Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models by Kennington, Casey; Lison, Pierre; Schlangen, David (2025) - We find that there is very little research on incremental dialogue management, offer some requirements for practical incremental dialogue management, and implications of incremental dialogue for embod- ied, robotic platforms in the age of large language models. Evaluating the potential utility of ASR N-best lists for incremental spoken dialogue systems. Keywords: action; asr; association; conference; david; dialogue; dialogue management; dialogue state; dialogue systems; end; et al; example; human; incremental; information; input; interaction; international; kennington; language; learning; level; linguistics; lison; management; models; nlu; output; pages; proceedings; processing; robot; schlangen; speech; state; systems; task; user; word; work
• A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human–Robot Interaction by Walker, Nicholas Thomas; Ultes, Stefan; Lison, Pierre (2025) - Moreover, GNNs also face difficulties when aggregating information across long paths in graphs, an “over-squashing” of graph information explored by Alon and Yahav (2020). This work did not however investigate the use of a natural language transformation of the graph, 67 WALKER, ULTES AND LISON relying instead on a text document constructed of structured representations of graph information in a similar manner to the semantic triples model employed in our experiments. Keywords: agent; approach; area; arxiv; conference; data; dialogue; dialogue state; environment; et al; generation; graph; graph information; hri; information; input; knowledge; knowledge graph; language; llm; llms; model; nodes; objects; observations; office; pages; preprint; response; robot; state; state graph; system; text; time; tour; triples; url; user; walker
• Investigating Proactivity in Task-Oriented Dialogues by Brenna, Sofia; Jezek, Elisabetta; Magnini, Bernardo (2025) - While this definition has the merit to relate proactivity with information content, which can be some- how located (i.e., annotated), it requires that proactive units (Balaraman and Magnini, 2020a) are exactly located within dialogue utterances, making the annotation effort excessively complex. We develop an annotation scheme and the guidelines to label the presence of proactivity in dialogue utterances and turns, and to tag the dialogue act displayed by proactive utterances. Keywords: acts; agent; annotation; chat; client; corpora; corpus; dialogue; dialogue act; doi; example; failure; goal; human; information; initiative; italian; jilda; language; level; linguistics; magnini; multiwoz; nespole; non; pages; proactive; proactivity; sub; task; turn; ubuntu; url; utterances; whatsapp
• A Few Shades of Supervision for Discourse Segmentation: Experiments on a French conversational corpus by PREVOT, Laurent; Muller, Philippe (2025) - 4.4 Discussion The key finding of our experiments on French conversations is that simple fine-tuning on gold labels performs well for elementary discourse unit segmentation. In a broader context, as discussed in Section 2, this paper provides a global view of the avail- able strategies for elementary discourse unit segmentation on spontaneous speech transcripts. Keywords: analysis; approach; corpus; data; des; dialogue; discourse; discourse segmentation; discourse units; disfluencies; elementary; errors; et al; example; fine; human; language; level; linguistics; markers; model; muller; pages; pause; prévot; segmentation; speech; table; task; training; transcripts; tuning; units
• Beyond semantics: the challenges of annotating pragmatic and discourse phenomena : Introduction to the special issue by Dipper , Stefanie; Zinsmeister, Heike; Webber, Bonnie (2025) - The evalua- tion of inter-annotation agreement shows that the task is more feasible for certain discourse relations and more subjective for others. The article by Thora Tenbrink, Kathleen Eberhard, Hui Shi, Sandra Kübler & Matthias Scheutz: “Annotation of negotiation processes in joint action dialogues” discuss another type of dialogue act annotation in terms of annotating activity coordination and goal negotiation pro- cesses, as well as belief states of the participants in dialogues that are conducted in course of a joint action. Keywords: agreement; annotation; article; authors; coherence; connectives; corpus; dialogue; discourse; focus; information; language; linguistics; relations
• Embodied Conversational Systems in Human–Robot Interaction: Introduction to the Special Issue by Gkatzia, Dimitra; Buschmeier, Hendrik; Foster, Mary Ellen; Strathearn, Carl (2025) - Roles and responsibilities of decision-making components in conversational robots. Hannes Ritschel, Thomas Kiderle, Klaus Weber, and Elisabeth André. Multimodal joke presentation for social robots based on natural-language generation and nonverbal behaviors. Keywords: dialogue; foster; generation; human; interaction; language; robot; robot interaction; systems

• Completions, Coordination, and Alignment in Dialogue by Poesio, Massimo; Rieses, Hannes (2010) - Our own account is based on such a theory, PTT (Poesio, 1994; Poesio and Traum, 1997; Poesio and Muskens, 1997; Poesio and Traum, 1998; Matheson, Poesio, and Traum, 2000) , a theory of dialogue semantics and dialogue interpretation that originated from work on the TRAINS-93 system (Allen et al, 1995). 6 A non-intentional analysis Pickering and Garrod (2004) while encouraging psycholinguists to take up dialogue as a valid area of research, argued that many aspects of dialogue interpretation—particularly priming at the lexical, syntactic, and referential level (Morton, 1969; Branigan et al, 2000)—can be explained without resorting to an intentional analysis, and sketched instead a model of interaction centered around the notion of ALIGNMENT between the dialogue participants’ models. Keywords: account; action; acts; alignment; case; clark; cnst; completions; contribution; coordination; dialogue; directive; discourse; du1.1; eine; example; figure; ginzburg; grounding; information; inst; intention; interpretation; k1.1; mit; model; new; plan; poesio; process; ptt; result; rieser; screw; section; semantic; situation; state; theory; traum; turn; type; update; utterance; view
• Modelling Structures for Situated Discourse by Asher, Nicholas; Hunter, Julie ; Thompson, Kate (2020) - This is a familiar point when performing an error analysis on the output of a learning program for discourse structure: a respectable F1 score at the level of instances might not mean much in terms of structure preservation; the predicted structures might still be useless as discourse structures, as argued in Ferracane et al. (2019). Examining how these nonlinguistic structures interact with structures determined by dialogue moves reveals new types of discourse structure and a novel perspective on discourse threads and goals. Keywords: annotations; asher; chat; core; corpus; dialogue; discourse; discourse structures; eeus; events; figure; game; game events; graph; hunter; moves; preservation; relations; structures; trade; turn
• A General, Abstract Model of Incremental Dialogue Processing by Schlangen, David; Skantze, Gabriel (2011) - Some of the characterisations of the behaviour of incremental modules are inspired by (Kilger and Finkler, 1995), but adapted and extended from incremental generation to the general case of incrementalprocessing. Thetransitive closure of this relation hence links system output IUs to a set of system input IUs. Keywords: abstract; buffer; dialogue; example; figure; incremental; information; input; ius; level; model; module; output; processing; right; schlangen; speech; state; system; � �
• Evaluation and Optimisation of Incremental Processors by Okko Buß, Timo Baumann; Schlangen, David (2011) - Hence, there is more to do than just comparing one actual output to one ideal output: We want to compare the content of incremental outputs, the timing of contributions to the result, and the evolution of the output over the course of processing the input sequence. Indecision is understandable at the beginning of input, but the more one has seen, the more not making a decision becomes just like making a wrong decision.6 4.2.2 TIMING METRICS Timing metrics measure when some notable event happens in incremental output relative to some reference time from the gold standard. Keywords: asr; correctness; dialogue; evaluation; figure; final; gold; incremental; input; metrics; output; performance; processing; processor; results; schlangen; section; standard; time; timing
• Incremental interpretation and prediction of utterance meaning for interactive dialogue by DeVault, David; Sagae, Kenji ; Traum, David (2011) - Completing user utterances To illustrate one use of the techniques described in the previous sections, we have implemented a prototype module that performs user utterance completion. We will turn to the understanding of partial user utterances in Section 4. Keywords: asr; clinic; completion; dialogue; figure; frame; maxf; model; mxnlu; nlu; output; partial; results; system; training; user; utterance; words
• The Dialog State Tracking Challenge Series: A Review by Williams, Jason D. ; Raux, Antoine ; Henderson, Matthew (2016) - 3.3 Discriminative models for dialog state tracking In contrast to generative models, discriminative approaches to dialog state tracking compute scores for dialog states with discriminatively trained conditional models of the form b′(s′) Dialog state tracking in situated environments – for example, robots or embodied agents – is also out of scope for this review, but it is noted that dialog state tracking is also used in this setting (Bohus and Horvitz, 2009; Keywords: asr; challenge; conf; data; dialog state; dialog systems; dialogue; dstc1; et al; henderson; models; proc; results; slot; slu; state tracking; states; systems; team; tracker; usa; user; usr; williams
• Recurrent Polynomial Network for Dialogue State Tracking by Sun, Kai ; Xie, Qizhe ; Yu, Kai (2016) - One mission is called dialogue state tracking (DST), which is a process to estimate the distribution of the dialogue states, an encoding of the machine’s understanding about the conversion as a dialogue progresses. Al- though the basic idea for transforming rules to neural networks has been there for many years (Cloete and Zurada, 2000), few work has been done for dialogue state tracking. Keywords: cmbp; data; dialogue; features; node; rpn; rule; state; tracking; value
• On Incrementality in Dialogue: Evidence from Compound Contributions by Howes, Christine; Purver, Matthew ; Healey, Patrick G. T.; Mills, Gregory J.; Gregoromichelaki, Eleni (2011) - Note, however, that these concerns only apply to same-person CCs andnot to cross-person CCs. Poesio and Rieser(2010) present a general model forcollaborative completions(a subclass of cross-person CCs) based in the PTT framework, using an incremental LTAG-based grammar and an information-state-basedapproach to context modelling. Keywords: antecedent; bnc; cases; ccs; chat; complete; compound; continuation; contributions; corpus; cross; dialogue; effect; end; participants; person; point; purver; speaker; split; start; text; turn; units
• Dialogue Act Classification, Instance-Based Learning, and Higher Order Dialogue Structure by Eugenio, Barbara Di; Xie, Zhuli ; Serafin, Riccardo (2010) - D&D: Dialogue Act Classification, Insta...re | Di Eugenio | Dialogue & Discourse Keywords: dialogue
• Discovering Rhetoric Agreement between a Request and Response by Galitsky, Boris (2017) - Rhetorical agreement may be present or absent in an RR pair, and the same applies to the relevance agreement. Some methods of measuring rhetorical agreement include considerations of relevance agreement whereas others do not. Keywords: actions; agreement; answer; cdt; cdts; dialogue; discourse; features; fig; galitsky; information; learning; number; pairs; parse; question; relations; request; response; rst; search; set; similarity; structure; sub; systems; text; training; trees; verbs
• User-Adaptive A Posteriori Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems by Komatani, Kazunori ; Hotta, Naoki; Sato, Satoshi ; Nakano, Mikio (2017) - ��/�� 0��# 1234��25 6 �7� �234��25 8%%/��%9 :2��4�2; <7� ;2=>2�� ����; ? ��@7=42 �2>�7 �� 2�� �7��� �� ��>2 A<7� �5������7�B C D7�525 � �7�7@7=���@@E FG�@��2 �7�5���7�H C I@@ =�J2� �� �5J���2 FK��� �7�5���7�H L MN F�@@H �����������; <7� �@7;25 �2;� L MO F2P�@45��= Q <7� �2;�H �����������; <7� ��7;; J�@�5���7� R�%� �� ����$ %� ��/%��� ���� �� 4;2�S; 5��@7=42 �2>�7; :2��4�2; ��5 �2<2�2��2 @�T2@; <7� ;2=>2�� ����; U72<<���2��;F�V TH W2�2 <�P25 �� � 2 2P�2��>2�� ? Keywords: adaptation; dialogue; restoration; system; user; utterance; ya �; ¢ �; ¤ �; � @7=42; � figure; � h; � z; � ¢; � £; � ¤; � �
• User Satisfaction Reward Estimation Across Domains: Domain-independent Dialogue Policy Learning by Ultes, Stefan; Maier, Wolfgang (2021) - Relevant Related Work Most of previous work on dialogue policy learning focuses on employing task success as the main reward signal (Gašić and Young, 2014; Gašić et al., 2014; Lemon and Pietquin, 2007; Daubigney et al., 2012; Levin and Pieraccini, 1997; Singh et al., 2002; Young et al., 2013; Su et al., 2015, 2016). This would mean that it would be less suitable to be applied to dialogue policy learning for different domains. Keywords: dialogue; dqn; enac; estimation; et al; interaction; learning; model; pages; policy; quality; rbi; reward; rts; satisfaction; success; system; table; task; ultes; user
• User Impressions of System Questions to Acquire Lexical Knowledge during Dialogues by Komatani, Kazunori; Ono, Kohei; Takeda, Ryu; Nichols, Eric; Nakano, Mikio (2022) - USER IMPRESSIONS OF SYSTEM QUESTIONS TO ACQUIRE LEXICAL KNOWLEDGE certain task-oriented dialogue systems can also engage in non-task-oriented dialogues (Lee et al., 2009; Dingli and Scerri, 2013; Kobori et al., 2016; Papaioannou and Lemon, 2017) because such dialogues are expected to build rapport (Bickmore and Picard, 2005; Lucas et al., 2018) between users and systems. 98 USER IMPRESSIONS OF SYSTEM QUESTIONS TO ACQUIRE LEXICAL KNOWLEDGE User impression data were collected by an experiment in which crowdsourced workers partici- pated in dialogue sessions, which involved three short interactions with a dialogue system. Keywords: annoying; category; content; correct; dialogue; et al; example; feature; figure; impression; knowledge; komatani; pages; proc; questions; scores; system; system questions; task; types; url; user; wrong
• Characterizing the Response Space of Questions: data and theory by Jonathan Ginzburg; Zulipiye Yusupujiang; Chuyuan Li; Kexin Ren; Aleksandra Kucharska; Lupkowski, Pawel (2022) - Our proposed typology identifies also other types of question responses that are not tackled by Berninger’s and Garvey’s proposal. In later work, an interesting typology of question responses was proposed as a result of an ex- tensive 10-language comparative project on question–response sequences in ordinary conversation. Keywords: ack; annotator; answer; bnc; cases; cht; classes; corpus; data; dialogue; dpr; english; f-1; ginzburg; group; ignore; ind; kucharska; motiv; pause; polish; precision; question; recall; ren; response; score; space; study; taxonomy; type; yusupujiang; łupkowski
• Studying Alignment in a Collaborative Learning Activity via Automatic Methods: The Link Between What We Say and Do by Norman, Utku; Dinkar, Tanvi; Bruno, Barbara; Clavel, Chloé (2022) - We investigate how these local alignment contexts could build to a function of dialogue level task success. We believe that this captures some local level alignment patterns that might have otherwise been overlooked when only considering dialogue level task success. Keywords: actions; activity; alignment; collaborative; dataset; dialogue; doi; error; establishment; expressions; information; instructions; interlocutors; learning; learning activity; lexical; mount; performance; results; says; solution; speech; study; success; task; task success; teams; test; times; utterance
• Multi-modal Anaphora and Broadcasting of Information by Gestural Post-holds by Rieser, Hannes (2024) - Agent(4) adds multi-modal information and sends the multi-modal Δi (doorway’(i), of’(i,a), λx(arch’(x))(a), small-arch(a)) out. For handling independent gesture information co-operating with speech information as in the arch’ and small arch case we need a communication vehicle, served by lY’s output-input agents. Keywords: agents; anaphora; arch; broadcasting; calculus; channel; ctnd; data; datum; dialogue; doorways; doorway’(i; entrance; figure; follower; gesture; giver; handshape; hedge; information; input; meaning; modal; output; pages; pond; rieser; right; route; sec; semantics; speech; vehicle; ù arch’(a; ù arch’(y; ù grey’(y; ù of’(i
• Common Ground inconsistencies in dialogue systems: conflict patterns implied by polar question forms by Di Maro, Maria; Origlia, Antonio; Cutugno, Francesco (2024) - More in detail, the following research questions will be investigated: • Main question: Does linguistic feedback in the form of different polar questions influence the capability of people to identify the cause of reported Common Ground inconsistencies? • Secondary question: Do different polar question forms influence the speed with which people take decisions when searching for the cause of reported Common Ground inconsistencies? More specifically, we investigated the following research questions: 139 DI MARO, ORIGLIA, CUTUGNO • Main question: Does linguistic feedback in the form of different polar questions influence the capability of people to identify the cause of reported common ground inconsistencies? • Secondary question: Do different polar question forms influence the speed with which people take decisions when searching for the cause of reported Common Ground inconsistencies? Keywords: action; bias; conflict; dialogue; error; et al; evidence; form; ground; hnpq; human; inconsistencies; information; interaction; maro; questions; recipe; sequence; slide; system; time; type; user

• The timing of prominence information during the resolution of German personal and demonstrative pronouns by Patterson, Clare; Schumacher, Petra (2020) - Keywords: prominence, anaphora, pronoun resolution, demonstrative, shallow processing, eye-tracking 1 Introduction Personal pronouns are referentially ambiguous, but they tend to refer to antecedents that are prominent in the prior discourse. Evidence from Schumacher and colleagues (Schumacher et al., 2015; 2016; 2017) shows that the findings from Garvey, Caramazza and Yates (1974) and Stevenson et al. (1994) regarding the importance of thematic role for pronoun resolution also applies to German pronouns. Keywords: antecedent; conditions; demonstrative; der; die; experiment; gender; german; information; np1; np2; personal; processing; prominence; pronoun; pronoun resolution; region; resolution; role; times
• The Use of Perspective Markers and Connectives in Expressing Subjectivity: Evidence from Collocational Analyses by Wei, Yipu ; Evers-Vermeul, Jacqueline ; Sanders, Ted J.M. (2020) - Shen Congwen (name) -1 renyi ‘righteousness’ -1 chunqiu ‘spring and autumn’ -1 bixu ‘must’ 1 yongtu ‘purpose’ -1 shihou ‘time’ 1 bu ‘no’ 1 dao ‘reach’ 1 wufa ‘have no mean’ 1 yuan ‘source’ -1 lai ‘come’ 1 zi ‘character’ -1 zhi ‘reach’ -1 Table 4. -1 dui ‘correct’ 1 yinyong ‘quote’ -1 youyu ‘since’ 1 juan ‘roll’ -1 zhi ‘reach’ -1 deng Keywords: analysis; chinese; clause; cognition; collocates; collocation; communication; connectives; context; discourse; expressions; genres; information; kejian; markers; narrative; perspective; relations; sanders; stance; subjectivity; suoyi; table; verbs; words
• Source vs. Stance: On the Relationship between Evidential and Modal Expressions by Tosun, Sümeyra ; Vaid, Jyotsna (2018) - Evidential source markers influence people’s reliability and certainty judgments. For source judgments, participants were instructed to decide on the source of information of each sentence based on 4 designated options: Hearsay, Inference, Assumption, and Conjecture. Keywords: assumption; confidence; conjecture; english; evidentiality; hearsay; inference; information; judgments; modal; sentences; source; speakers; turkish
• Active prediction of syntactic information during sentence processing by Ilkin, Zeynep; Sturt, Patrick (2011) - Eye movements and parafoveal word processing in reading Chinese. In other words, the proportion oftrials in whichbottle received a fixation during initial reading was greater in the unpredictable condition than the predictable condition. Keywords: dependency; effect; et al; eye; fixation; information; noun; plural; prediction; processing; reading; region; results; sentence; skipping; subject; time; word
• Identifying "aboutness topics": two annotation experiments by Cook, Philippa ; Bildhauer, Felix (2013) - Institut für Deutsche und Niederländische Philologie Freie Universität Berlin 14195 Berlin, Germany Editor: Stefanie Dipper, Heike Zinsmeister, Bonnie Webber Abstract This paper deals with the annotation of “aboutness topic” (also known as “sentence topic”) in natu- rally occurring data. In the present paper, we will take a closer look at the annotation of “aboutness topics” (also known as “sentence topics”) in naturally occurring data. Keywords: aboutness; agreement; annotation; annotators; cases; clause; comment; data; discourse; entity; experiment; focus; guidelines; information; krifka; non; section; sentence; structure; subject; thetic; topic
• Focus Triggers and Focus Types from a Corpus Perspective by Riester, Arndt ; Baumann, Stefan (2013) - In addition to that, the (pairs of) foci may also be called contrastive foci, due to the presence of overt alternatives. This will become clear in Section 4, when we will discuss whether an observed nuclear pitch accent is used to express contrastive focus or not. Keywords: accents; alt; alternative; annotation; baumann; corpus; discourse; example; foci; focus; information; level; new; overt; pages; phrase; pitch; prosodic; question; riester; section; semantics; sentence; structure; types
• A Neural Approach to Discourse Relation Signal Detection by Zeldes, Amir; Liu, Yang (2020) - Amanda Stent Submitted 09/2019; Accepted 02/2020; Published online 07/2020 Abstract Previous data-driven work investigating the types and distributions of discourse relation signals, including discourse markers such as ‘however’ or phrases such as ‘as a result’ has focused on the relative frequencies of signal words within and outside text from each discourse relation. In fact, only about 8.3% of the tokens correctly identified by the model in Table 6 below are of the DM type, whereas about 7.2% of all tokens flagged by human annotators were DMs, meaning that the model frequently matches non-DM items to discourse relation signals (see Performance on Signal Types below). Keywords: annotations; approach; classification; context; corpus; data; detection; discourse; discourse relation; discourse signal; evaluation; gold; human; information; liu; markers; model; nucleus; pages; relation; relation signal; rst; satellite; signal; table; text; tokens; types; word; work; zeldes
• An Analysis of Japanese Sentence-final Particle Yone: Compare Yone and Ne in Response by Xu, Jun (2021) - When speaker G tells her the classmate was not at school yesterday (line 4), speaker B produces in line 5 a response with yone and “a::.” (15) 1 B: → gakkoo kiteru↑ kare school coming he 2 C: In line 11, speaker G supports speaker B’s view that kittens are cute by using ne. Keywords: answer; awareness; data; example; information; japanese; line; question; response; sentence; speaker; study; yone
• Pragmatic uses of I don’t know, boosters, and hedges in text and talk by Nguyen, Allison; Fox Tree, Jean (2025) - We predict that storytelling chit-chat will more closely resemble naturalistic conversation (the chat portions of the Artwalk and IM corpora) than task conversation (the task portions of the Artwalk and IM corpora) for I don’t know. However, there was a difference in the number of I dunnos used in task related conversation, with more I dunnos in friend dyads working on tasks compared to dyads of strangers (t(25.45) = 2.37, p = .03). Keywords: artwalk; boosters; chat; chit; commitment; conversation; corpus; hedges; idk; information; kinda; task; times; uses; words
• Enhancing Long-term RAG Chatbots with Psychological Models of Memory Importance and Forgetting by Sumida, Ryuichi; Inoue, Koji; Kawahara, Tatsuya (2025) - The forgetting process is executed only after the user finishes a conversation, ensuring that memory importance—calculated using retrieval frequency and other dynamic metrics—reflects the full interaction. MemoryBank assesses the importance of a memory based solely on retrieval counts, whereas LUFY evaluates memory importance using six memory-related metrics, as depicted in Figure 2. Keywords: analysis; chatbot; conversation; events; figure; forgetting; future; human; importance; information; llm; lufy; memories; memory; memorybank; metrics; models; rag; retrieval; score; session; system; table; term; user; utterance

• HILDA: A Discourse Parser Using Support Vector Machine Classification by Hernault, Hugo; Prendinger, Helmut; Verle, David A. du; Ishizuka, Mitsuru (2010) - This corpus contains 700 expository dialogues labeled with dialogue acts, paired with human-authored, equiv- alent monologues annotated with RST discourse relations. Figure 2 shows two types of discourse relations in RST: hypotactic (‘mononuclear’) and parat- actic (‘multi-nuclear’). Keywords: discourse; discourse parser; features; hilda; level; marcu; nucleus; parser; performance; relations; rst; satellite; segmentation; sentence; set; span; structure; system; table; text; tree
• Corpus-driven Semantics of Concession: Where do Expectations Come from? by Robaldo, Livio ; Miltsakaki, Eleni (2014) - In formal terms, we propose to represent semantic concessive relations via the following general pattern in Hobbs’ logic: (35) (exist (sac sc ec ee ed) ∧ (partialInstance sc sac) ∧ (Φ sc ec ee) ∧ (Rexist ec) ∧ (Rexist ed) ∧ (inconsistent ee ed) ) 27 ROBALDO AND MILTSAKAKI where Φ is a generic predicate referring to the underspecified entailment that creates the expectation; it corresponds to Winter&Rimon’s ‘→’. Many have tried to sub-categorize Concession and to define formal criteria to both distinguish its subtypes as well as for distinguishing Concession from the (similar) semantic relation of Contrast. Keywords: argc; argd; cases; causal; concession; contrast; discourse; eventuality; expectation; hobbs; implication; john; lagerwerf; pdtb; predicate; relations; rule; semantics; speaker
• Evaluation in Discourse: a Corpus-Based Study by Benamara, Farah ; Asher, Nicholas ; Mathieu, Yvette Yannick ; Popescu, Vladimir ; Chardon, Baptiste (2016) - 5.3.4 Segment type, segment polarity, and overall opinion We investigated whether implicit opinion segments contribute to the author’s global opinion on the main topic of the document. Segment opinion type mainly follows Wiebe et al. (2005); Toprak et al. (2010) and Liu (2012). Keywords: analysis; annotation; asher; category; corpus; discourse; discourse relations; discourse structure; document; edus; evaluation; expression; fmr; fnr; french; implicit; level; movie; opinion; opinion expression; pages; polarity; proceedings; relations; results; reviews; segment; sentiment; structure; subjectivity
• Categories of coherence relations in discourse annotation by Scholman, Merel C.J. ; Evers-Vermeul, Jacqueline ; Sanders, Ted J.M. (2016) - Over the last decade, annotating coherence relations has gained increasing interest of the linguistics research community. In this article, we investigate whether non-trained, non-expert annotators are capable of annotating coherence relations. Keywords: agreement; annotation; annotators; causal; coherence; coherence relations; discourse; instruction; non; order; polarity; primitive; relations; sanders; segments; source; step; tests
• A corpus-driven approach to discourse organisation: from cues to complex markers by Péry-Woodley, Marie-Paule ; Ho-Dac, Lydia-Mai ; Rebeyrolle, Josette ; Tanguy, Ludovic ; Fabre, C`ecile (2017) - The contribution of linguistic knowledge to the interpretation of text structures. For example, (sub)headings may be considered as ES-cues only in specific genres or text types. Keywords: adverbials; annodis; annotation; approach; closure; corpus; cues; dac; data; des; discourse; discourse markers; discourse organisation; discourse relations; ess; example; features; item; les; level; lexical; markers; organisation; paragraph; péry; rebeyrolle; relations; section; signalling; structures; sub; text; trigger; type; woodley
• Just because: In search of objective criteria of subjectivity expressed by causal connectives by Levshina, Natalia ; Degand, Liesbeth (2017) - Objective causal relations express causality between events in the real world, as in (1), whereas subjective causal relations express the speaker’s motivation for mental conclusions or speech acts, as in (2)1. This variable was added because manual analysis has shown that subjective causal relations tend to co- occur with evaluative adjectives and/or adverbs, while objective causal relations do not (Pander Maat & Degand, 2001; Pit, 2006; Sanders & Spooren, 2015). Keywords: causal; clause; connectives; data; degand; discourse; dutch; english; model; objective; omdat; opus; predicate; relations; sanders; subject; subjectivity; subordinate; variables; want
• Asymmetries between interpretation and production in Catalan pronouns by Mayol, Laia (2018) - Carminati, M. N. (2002), The processing of Italian subject pronouns, PhD thesis, University of Massachusetts. La Jèssica li va servir l’arròs a la Carme. Keywords: bias; condition; data; experiment; factors; free; interpretation; model; object; overt; production; pronoun; reference; referent; referring; relations; subject; type
• Reasoning Between the Lines: a Logic of Relational Propositions by Potter, Andrew (2019) - Relational propositions, the implicit assertions that correspond to RST relations, are defined using standard logical operators and rules of inference. If it were the case that RST relations corresponded one to one with logical operators and units with propositions, the task of restating RST analyses as Boolean expressions would not be interesting. Keywords: analysis; discourse; effect; logic; mann; nucleus; propositions; reader; relations; rst; satellite; structure; text; thompson;  
• How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations by Demberg, Vera ; Scholman, Merel C.J.; Asr, Fatemeh Torabi (2019) - The algorithm proposed in this article allowed us to align 76% of PDTB discourse relation annotations to corresponding RST annotations. We conclude that our manual inspection of a representative sample of instances confirms that our algorithm finds the right alignment between corpora in the majority of cases and thus provides us with reliable data for cross-corpora analysis of relation annotation. Keywords: annotation; annotators; arguments; cases; connectives; contrast; differences; discourse; discourse annotation; discourse relations; example; frameworks; instances; iso; labels; mapping; pdtb; pdtb annotation; pdtb relations; proposals; relation labels; relations; rst; segments
• Signaling of Causal Relations in Spanish: Variety, Functionality, and Specificity by Ibáñez, Romualdo ; Moncada, Fernando ; Cárcamo, Benjamín ; Marín, Valentina (2020) - Keywords: Causal coherence relations, connectives, cue phrases, Spanish SIGNALING OF CAUSAL COHERENCE RELATIONS IN SPANISH 41 1 Introduction Based on the assumption that there is no one-to-one mapping between connective expressions and coherence relations, scholars have devoted considerable attention to the description of coherence relation signaling. To go further into the description of these phenomena would not only widen our understanding of the way coherence relations are signaled in Spanish, it would also contribute to the delineation of the way connective expressions and causal coherence relations interact across languages. Keywords: argument; causal; claim; coherence; coherence relations; condition; connective; contrast; corpus; discourse; event; expressions; ibáñez; porque; que; relations; sanders; signal; signaling; spanish; specificity; types
• Question Generation from Concept Maps by Olney, Andrew M. ; Graesser, Arthur C. ; Person, Natalie K. (2012) - Given the success of representation-free approaches to question answering, a pertinent ques- tion is whether the same can be true for question generation (Yao 2010). Previous work on question generation has demonstrated that named entities and adjunct roles may both be mapped to question type categories in a straightforward way. Keywords: asking; categories; causal; concept; editors; et al; example; graesser; knowledge; learning; maps; model; pages; person; predicates; proceedings; question; question generation; relations; research; sentence; student; table; triples; type
• Subjectivity in Spanish Discourse: Explicit and Implicit Causal Relations in Different Text Types by Santana, Andrea ; Spooren, Wilbert ; Nieuwenhuijsen, Dorien ; Sanders, Ted (2018) - For example, in French, car (‘for’) and puisque (‘since’) have been recognized as connectives that are used preferentially to express subjective meanings as opposed to parce que (‘because’), that has been identified as a connective that has a more general meaning and a preference to express objective relations (Degand & Pander Maat, 2003; Zufferey, 2012); in Mandarin-Chinese, kĕjian (‘so/therefore’) prefers to express subjective relations, whereas yīn’er (‘as a result’) tends to express objective meanings (Li, et al., 2013; Wei, et al., 2018). See also Note 4. SANTANA, SPOOREN, NIEUWENHUIJSEN AND SANDERS 166 ya que (‘since’) is a connective used preferentially for expressing subjective relations. Keywords: act; analysis; cases; causal; coherence; connectives; context; corpus; discourse; domain; fact; identity; journalistic; modality; objective; presence; que; relations; sanders; soc; spanish; speaker; speech; spooren; study; subjectivity; table
• Using the Cognitive Approach to Coherence Relations for Discourse Annotation by Hoek, Jet; Evers-Vermeul, Jacqueline ; Sanders, Ted J. M. (2019) - Abstract The Cognitive approach to Coherence Relations (Sanders, Spooren, & Noordman, 1992) was originally proposed as a set of cognitively plausible primitives to order coherence relations, but is also increasingly used as a discourse annotation scheme. Keywords: discourse annotation, coherence relations, corpus annotation, Cognitive approach to Coherence Relations 1 Introduction Annotating coherence relations refers to the process of attributing labels that best capture the relation inferred between two segments in a text to that relation. Keywords: additive; annotation; basic; causal; ccr; coherence relations; discourse; discourse annotation; distinction; evers; hoek; new; objective; order; primitives; relations; sanders; section; segments; source; spooren; taxonomy; value; vermeul
• Linguistic Tests for Discourse Relations by Versley, Yannick ; Gastel, Anna (2013) - Modeling the annotation process as tagging each inter-topic boundary with or without a transitional EDU yields a value of κ = 0.85, or a positive specific agreement of F1 = 0.88. 168 LINGUISTIC TESTS FOR DISCOURSE RELATIONS IN TÜBA-D/Z 5.2 Identifying Problematic Areas Table 4 shows the most frequent confusions between discourse relations in cases where different an- notators could agree on a span, but chose different relations, collected over a larger sample of docu- ments annotated by at least two trained annotators. More so than for referential an- notation, discourse relation annotation is rendered difficult by the absence of a general consensus on the underlying linguistic phenomena that should be targeted, as well as by a lack of strong predictions on the possible or permissible interactions between these phenomena. Keywords: annotation; arg1; arg2; case; coherence; contrast; corpus; discourse; discourse annotation; discourse relations; discourse segments; discourse structure; et al; example; explanation; knott; question; relations; result; rst; sanders; scheme; segments; structure; tests; text; topic; treebank; tüba
• Annotation upon Annotation: Adding Signalling Information to a Corpus of Discourse Relations by Taboada, Maite ; Das, Debopam (2013) - 6 Results Among the 1,304 relations examined, the distribution of signalled relations (indicated either by discourse markers or by some other signal) and unsignalled relations (not indicated by any signal) is provided in Table 4. The detailed, extensive analysis of signals in the corpus can aid research in the automatic parsing of discourse relations. Keywords: annotation; coherence; corpus; discourse; discourse markers; discourse relations; elaboration; entity; lexical; list; markers; relations; rst; semantic; signalling; signals; syntactic; text; types
• A Discriminative Analysis of Fine-Grained Semantic Relations including Presupposition: Annotation and Classification by Tremper, Galina ; Frank, Anette (2013) - However, we adhere to this distinction, as introduced by Fellbaum (1998), as indeed we find clear differences in the inferential properties of these two types of verb relations. These properties will establish important criteria for the automatic classification of verb relations into the target classes. Keywords: analysis; annotation; annotators; classification; context; corpus; discriminative; entailment; features; inclusion; inference; negation; pairs; presupposition; properties; question; relations; results; score; semantic; set; table; task; temporal; type; verb; verb pairs
• Examples and Specifications that Prove a Point: Identifying Elaborative and Argumentative Discourse Relations by Scholman, Merel C.J. ; Demberg, Vera (2017) - Related approaches using crowdsourcing for discourse relation annotation have been put forward by Kawahara et al. (2014) and Rohde et al. (2016). 5.2 Methodological remarks on crowdsourcing discourse relation annotations The crowdsourcing method used in the current study was shown to be relatively reliable for acquir- ing discourse annotations: The participants were able to insert the predicted connectives in filler items with high accuracy. Keywords: argumentative; causal; connectives; discourse; example; insertions; instantiation; items; label; participants; pdtb; relations; rst; segment; specification; specification relations
• Signalling Implicit Relations: A PDTB - RST Comparison by Poláková, Lucie; Mírovský, Jiˇrí ; Synková, Pavlína (2017) - Red arrows/polylines represent RST relations; orange arrows represent implicit discourse relations from the PDTB. A preparatory survey was conducted by hand (18 matches with RST relations detected). Keywords: annotation; arguments; corpus; data; discourse; discourse relations; lexical; pdtb; pdtb relations; relations; rst; semantic; signal; signalling; single; syntactic; treebank; types
• Discourse Relations and Connectives in Higher Text Structure by Polakova, Lucie; Mírovský, Jiří; Zikánová, Šárka; Hajičová, Eva (2021) - 4.1 – configurations of pairs of discourse relations, a study carried out on the basis of a similar research by the PDTB group and, like this study, contributing to the debate on acceptable “shapes” of an interconnected coherence representation of a text; 4.2 – hierarchies of nested discourse relations – a study that reveals if local discourse relations, without having the underlying assumption of hierar- chy, also exhibit some type of hierarchical structure; 4.3 – paragraph-initial senses and connectives, a survey on cross-paragraph coherence in comparison to intra-paragraph settings; and 4.4 – rela- tions with large arguments, as these are rather unexpected/unusual in local settings and can denote possible non-elementary units of higher text structuring.11 4.1 Configurations of Close Relation Pairs For this part of the analysis, and also for the subsequent one described in 4.2, we take advantage of the fact that the corpora used in the PDTB and our studies are comparable in many aspects (as mentioned earlier) and also contain a similar number of annotated discourse relations (approx. Nodes represent individual clauses, root nodes refer to individual sentences, semantic types of discourse relations are highlighted in orange, connectives in green. Keywords: = =; analysis; annotation; arguments; coherence; connectives; cross; data; discourse; discourse connectives; discourse relations; hierarchies; inter; left; mírovský; paragraph; patterns; pdit; pdtb; poláková; relations; right; rst; sentence; structure; study; table; text; treebank
• The effect of domain knowledge and implicitation on discourse relation inferences by Marchal, Marian; Scholman, Merel; Demberg, Vera (2022) - Non-connective linguistic cues for discourse relations (i.e. words or phrases that tend to co-occur statistically with certain discourse relations) might thus play a role in inferring discourse relations. In addition, if low-knowledge readers’ interpretations are guided by their cognitive biases, it is predicted that these readers will infer more continuous and causal discourse relations than high- knowledge readers. Keywords: connective; contrast; corpus; cues; discourse; discourse relations; domain knowledge; effect; expertise; experts; items; knowledge; knowledge readers; participants; readers; relations; study; text
• Exploring the Sensitivity to Alternative Signals of Coherence Relations: The Case of French Speaking Teenagers by Tskhovrebova, Ekaterina; Zufferey, Sandrine; Gygax, Pascal (2023) - For instance, assessing the interaction between non-connective list signals, additive and consequence connectives for readers’ propensity to generate inferences of list relations would enable us to evaluate whether these relations are still inferred from non-connective signals. In order to explore this relation further, we will extend the study of non-connective list signals on a younger population, who has even less linguistic experience than adults and is probably still acquiring a sensitivity to such signals. Keywords: additive; adults; analysis; coherence; connective; continuations; experiment; list; list continuations; list relation; list signals; outre; participants; relations; sensitivity; sentences; signals; task; teenagers
• German Modal Particles as Discourse Signals by Seemann, Hannah; Scheffler, Tatjana (2025) - Discourse particles “embedded”: German ja in adjectival phrases. Keywords: Modal particles; discourse particles; discourse relations; discourse signals; ja; doch; German 1. Keywords: causal; condition; connective; context; das; discourse; discourse particles; discourse relations; discourse signals; doch; doi; effect; evidence; german; markers; modal; nucleus; participants; particles; processing; relations; satellite; sentence; signals; study
• Speech acts that support other speech acts by Jasinskaja, Katja; Zickenheiner, Frank (2025) - There is a vast theoretical tradition that recognises the central role of speech act goals in the structuring of discourse, most notably Grosz and Sidner (1986), as well as Roberts (1996) and Ginzburg (2012) with questions under discussion as a specific conceptualisation of goals. Clark’s levels of action are a more useful framework for mapping the entire space of speech act goals because it takes the state of the addressee systematically into account. Keywords: action; acts; addressee; attention; belief; coherence; discourse; doi; evidence; goal; hearer; level; relations; speaker; speech; speech act; support; support relations; understanding; uptake; url; utterance

• Cross-domain analysis of discourse markers in European Portuguese by Cabarrão, Vera ; Moniz, Helena ; Batista , Fernando ; Ferreira, Jaime ; Trancoso, Isabel ; Mata, Ana Isabel (2018) - Since we aim at performing a general characterization of discourse markers and not to explore the functions of each marker individually, we decided not to include these structures when they do not co-occur with other discourse markers. Cross-domain analysis of discourse markers in European Portuguese Vera Cabarrão VERACABARRAO@GMAIL.COM L2F, INESC-ID FLUL/CLUL Helena Moniz HELENA.MONIZ@INESC-ID.PT L2F, INESC-ID FLUL/CLUL Fernando Batista FERNANDO.BATISTA@INESC-ID.PT L2F, INESC-ID Instituto Universitário de Lisboa (ISCTE-IUL) Keywords: batista; classification; corpora; corpus; data; dialogues; discourse markers; disfluencies; domain; european; events; features; initial; lectures; metadata; moniz; prosodic; results; set; speech; study; trancoso; turn; university; words; work
• ChangeMyView Through Concessions: Do Concessions Increase Persuasion? by Musi, Elena ; Ghosh, Debanjan ; Muresan, Smaranda (2018) - Argumentative concessions In order to answer our research question — whether argumentative concessions increase persuasion — we need to provide a definition of argumentative concessions. We have tested the statistical significance of the distribution of argumentative concessions on the manually labeled sets using χ2 test: the results are not significant at p < 0.05 on training and test 121 MUSI, GHOSH AND MURESAN Marker ∆-dev no-∆-dev ∆-test no-∆-test ∆-unlabel no-∆-unlabel but 49 57 51 47 1100 793 however 2 4 - - - - though 4 5 - 1 8 2 while 1 2 - - - - total 56 68 52 48 1112 795 Table 6: Distribution of predicted argumentative concessions in ∆ and no-∆ comments sets, while they are significant on dev set, where argumentative concessions are less frequent in winning arguments. Keywords: arg; changemyview; concessions; corpus; data; dev; discourse; distribution; expert; features; instances; patterns; persuasion; self; set; speaker; test; training
• A corpus of science journalism for analyzing writing quality by Louis, Annie ; Nenkova, Ani (2013) - For example, we might expect that good science articles are informative and contain more sentences that define and explain aspects of the research. Science articles are also sometimes written as a story and this style of writing creates sentences associated with the narrative and dialog in the story. Keywords: annotations; articles; categories; category; clusters; content; corpus; data; example; features; goals; journalism; level; louis; nenkova; pages; proceedings; quality; research; science; sentences; set; specificity; table; text; text quality; topic; writing
• Boon or Bane? Discursive Construction of the Shale Gas Controversy by Koca-Helvacı, Zeynep Cihan (2017) - The studies mentioned in this section showed that previous linguistic research on shale gas discourse tends to focus on macro-linguistic structures such as frames and storylines whereas micro- KOCA-HELVACI 132 linguistic structures such as lexical choices, agency and argumentative strategies haven’t been studied in much detail. The findings of the study show that the advocates presented shale gas as a bonus for the crisis-struck American society through discourse of altruism and solidarity. Keywords: aaf; actors; analysis; categories; corpus; discourse; energy; environmental; extraction; fracking; fracturing; gas; group; msc; public; shale; shale gas; strategies; table; terms; wodak
• Event and Entity Coreference Across Five Languages: Effects of Context and Referring Expression by Bevacqua, Luca; Loáiciga, Sharid; Rohde, Hannah; Hardmeier, Christian (2021) - The OntoNotes corpus (Pradhan and Xue, 2009), for instance, although the largest in the community, does not include annotations of event entities coreferential with pronouns. Corpora with a richer annotation of event pronouns exist, but are much smaller. Keywords: alternation; antecedents; aspect; coreference; corpus; data; english; entities; entity; event; form; french; german; italian; languages; model; non; pronouns; results; spanish; use; verbs
• Opinion Piece: Can we Fix the Scope for Coreference? Problems and Solutions for Benchmarks beyond OntoNotes by Zeldes, Amir (2022) - But ignoring ‘diffi- cult’ predicate NPs as part of coreference annotation will lead to many gaps in what practitioners using coreference resolution might expect or could harness. And if something is supposed to be recoverable from syntax, this should not move us to exclude it from coreference annotation – oth- erwise we are effectively mandating that any coreference resolution system will also have to tackle syntactic parsing. 3.2 How about semantics? Keywords: anaphora; annotation; cases; coreference; coreference resolution; corpus; data; english; entity; et al; example; generic; guidelines; gum; modifiers; nps; ontonotes; pages; predication; problems; proceedings; resolution; scope; zeldes

• Holistic Discourse Coherence Annotation for Noisy Essay Writing by Burstein, Jill ; Tetreault, Joel ; Chodorow, Martin (2013) - A system’s precision on high coherence essays, for example, is the number of essays that both the system and the human annotator agreed are “high”, divided by the number of essays that the system labeled “high”. In Section 2, we discuss computational approaches to the evaluation of discourse coherence and related work on annotation methods used to build and evaluate systems for predicting text coherence and readability. Keywords: annotation; annotators; burstein; coherence; coherence quality; data; discourse; discourse coherence; essay; features; high; point; quality; score; system; text; writing
• A modular architecture for creating multimodal embodied agents with an episodic Knowledge Graph as an explainable and controllable long-term memory by Baier, Thomas; Báez Santamaría, Selene; Vossen, Piek (2025) - By analyzing the recorded interaction, we can compare agents and agent components and study their interactive behavior with people and other agents. Evaluating agent interactions through episodic knowledge graphs. Keywords: agent; annotation; architecture; audio; bus; components; data; dialog; e l; e r; e s; ekg; emissor; event; event bus; interaction; knowledge; multimodal; output; platform; processing; signal; t e; text; vossen

• Co-authorship of Joint utterances in Japanese by Obana, Yasuko ; Haugh, Michael (2015) - The two utterances constitute a co-authored joint utterance, in which Tomoko‟s predicate noun (Hooryuuji) is shared between the two independent utterances. Because of this, one may wonder if co-authored joint utterances can be analysed with reference to anaphoric relations alone. Keywords: clause; construction; continuation; example; japanese; joint; line; speaker; speaker‟s; tcu; tcus; tomoko; units; utterance
• Primary and secondary discourse connectives: definitions and lexicons by Danlos, Laurence ; Rysova, Katerina ; Rysova, Magdalena ; Stede, Manfred (2018) - Therefore, we believe that a systematic treatment of secondary connectives — and having them play a similar role to that of primary connectives — can be highly beneficial for such parsers, because delegating cases like (1b) to the “explicit” module would reduce the number of instances to be handled by the much more ambitious “implicit relation” module. These expressions differ in many ways, and we divide them into three groups following the concept of Rysová and Rysová (2014): primary connectives (4a), henceforth in magenta; secondary connectives (4b-d), in blue; and free connecting phrases (4e), underlined. Keywords: arg1; arg2; connectives; core; discourse; discourse connectives; example; fred; german; lexicon; primary; reason; relation; rysová; secondary; sense; stede; unit; word
• Calling things by their names: Towards a unified account for name-informing and mixed quotation by Härtl, Holden (2025) - This paper explores the semantic connection between mixed quotation and name-informing quotation, proposing a unified account for both. While mixed quotation combines direct quotation with indirect reporting, name-informing quotation highlights the linguistic shape of a concept’s conventionalized name. Keywords: account; argument; condition; content; example; issue; mqs; naming; niq; predicate; quotation; quotes; rejections; semantic

• Spectral decomposition method of dialog state tracking via collective matrix factorization by Perez, Julien (2016) - In the next section, we present a decompositional approach of dialog state tracking that aims at reconciling the two main approaches of the state of the art while leveraging on the current advances of low-rank bilinear decomposition models, as recalled in Ma et al. (2014), that seems particularly adapted to the sparse nature of dialog state tracking tasks. Dialogue & Discourse 7(3) (2016) 34 –46 doi: 10.5087/dad.2016.304 Spectral decomposition method of dialog state tracking via collective matrix factorization Julien Perez JULIEN.PEREZ@XRCE.XEROX.COM Xerox Research Center Europe Grenoble, 38000, France Editor: Jason D. Williams, Antoine Raux, and Matthew Henderson Submitted 04/15; Accepted 02/16; Published online 04/16 Abstract The task of dialog management is commonly decomposed into two sequential subtasks: dia- log state tracking and dialog policy learning. Keywords: approach; dialog; dialog state; matrix; model; state; state tracking; system; task; tracking; user; variables; williams
• Dialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking by Lee, Byung-Jun ; Kim, Kee-Eung (2016) - With this approach, we can preserve the intu- itiveness and compositionality of generative dialog state trackers while autonomously bookkeeping appropriate information over time, which results a boost in performance. This setting of parameters enable the real-time tracking of dialog state, while preserving most of the information required. Keywords: action; dialog; dialog state; dstc2; history; model; state; system; tracker; tracking; user
• Cognitive and social delays in the initiation of conversational repair by Mertens, Julia Beret ; de Ruiter, J. P. (2021) - For details on missing data, see our JASP file at https://osf.io/h5ysb/. 4.3 Cognitive Factor Regression We regressed the log-transformed OIR FTO on all cognitive factors (trouble source turn FTO, dis- jointed status, length in both words and duration, average word frequency and syllable rate). In summary, one explanation for the increased OIR FTO after trouble source turns with less discourse context is that the listener needed more time to direct their attention to the trouble source turn. Keywords: class; cognitive; conversation; duration; fto; ftos; model; oir; oirs; repair; source; source turn; trouble; trouble source; turn
• Narrative Elements in Expository Texts: A Corpus Study of Educational Textbooks by Sangers, Nina L.; Evers-Vermeul, Jacqueline; Sanders, Ted J.M.; Hoeken, Hans (2021) - Finally, future research could focus on the presumed rationale behind including narrative elements in educational texts: are narrative educational texts indeed more interesting to read and easier to understand than expository educational texts? This strict interpretation excludes educational texts with only one particularized event from a classification as narrative texts. Keywords: biology; characters; content; dutch; elements; events; expository; geography; gh texts; grade; history; history texts; human; model; narrative; narrative elements; representative; sangers; texts
• Form and Function of Connectives in Chinese Conversational Speech by Wu, Nien-Heng; Tseng, Shu-Chuan (2023) - Durational cues of the preceding context enable distinguishing Sentential use from discourse uses of Conclusion, Elaboration, and Resumption of connectives. Moreover, they noted that discourse uses of alors was almost never followed by a silent pause. Keywords: chinese; conclusion; connectives; discourse; discourse functions; disfluency; elaboration; et al; form; functions; inhale; mandarin; model; pause; resumption; ránhòu; sentential; speaker; speech; tokens; topic; use; uses; wang

• Using Gestures to Resolve Lexical Ambiguity in Storytelling with Humanoid Robots by Scholl, Catelyn ; McRoy, Susan (2019) - If coordinated beat gestures are enough, then, in addition to assessing the impact on understanding homophones, one could explore how robot gesture affects the retention of narrative details, using a story that has distinct characters, setting, or events. Keywords: lexical ambiguity, speech prosody, homophones, iconic gestures, deictic gestures 1. Keywords: children; control; gestures; group; homophones; iconic; post; robot; speech; story; test
• Attribution and the discourse structure of reports by Maier, Emar (2023) - That is what happens in indirect discourse reports, and it is exactly this type of ‘loose’ characterizing that is formalized explicitly in our original formulation of the semantics of ATTRIBUTION in (10). In order to correctly infer coherence (and anaphoric) connections between multi-sentence quotations and derive graph structures like (27), the Glue Logic needs to have some access to the semantic content of quoted discourse units as well as their forms. Keywords: attribution; characterization; content; discourse; doi; drs; event; form; maier; quotation; relation; reports; sdrt; semantics; speech; structure; unit
• Laughter use by virtual agents increases task success by Ludusan, Bogdan; Wagner, Petra (2025) - Experiments to quantify the effect of agent laughter use on the perception of the agent by their human interlocutor or on the overall interaction have also been conducted. 1. https://cloud.google.com/text-to-speech 11 LUDUSAN AND WAGNER During the recording session, the experimenter played through loudspeakers the line corresponding to the agent (laughter condition) and the speaker would respond with the appropriate line. Keywords: agent; apartment; conditions; human; interaction; laughter; participants; rating; speech; success; task; use

• G-Asks: An Intelligent Automatic Question Generation System for Academic Writing Support by Liu, Ming; Calvo, Rafael A.; Rus , Vasile (2012) - The input to G- Asks is a literature review paper stored at the sentence level after the preprocessing in iWrite and the output is a set of generated questions used by iWrite, which delivers the questions to the student author. First, we evaluated G-Asks’s performance with respect to citation extraction ability and semantic correctness of generated questions. Keywords: approach; asks; citation; feedback; generation; graesser; human; literature; method; opinion; quality; questions; research; result; sentence; students; study; system; table; verb; writing
• Scoring Coreference Chains with Split-Antecedent Anaphors by Paun, Silviu; Yu, Juntao; Moosavi, Nafise Sadat; Poesio, Massimo (2023) - Split-antecedent anaphoric references are rarer compared to single entity anaphoric references, at least for the case of plural split antecedent references (split discourse deictic references are much more common). Before introducing the proposed extensions to additionally evaluate split-antecedent references, we briefly discuss in this Section the metrics standardly used to evaluate single antecedent reference and their existing definitions. Keywords: anaphora; anaphoric; antecedent; antecedent anaphors; antecedent references; association; coreference; discourse; entities; entity; et al; evaluation; key; linguistics; links; mentions; metrics; poesio; resolution; response; score; section; set; sets; split; system; yu et

• Creating Conversational Characters Using Question Generation Tools by Yao, Xuchen ; Tosch, Emma ; Chen, Grace ; Nouri, Elnaz ; Artstein, Ron ; Leuski, Anton ; Sagae, Kenji ; Traum, David (2012) - These question- answer pairs form knowledge bases for a series of virtual question answering characters. The remainder of the article gives an overview of question generation and the tools we use, describes in detail the setup and results for the three experiments, and concludes with broader im- plications and directions for further study. Keywords: answer; character; experiment; generation; hand; knowledge; leuski; pairs; proceedings; question; set; source; sword; table; test; text; topics; traum
• Question Generation based on Lexico-Syntactic Patterns Learned from the Web by Curto, Sergio ; Mendes, Ana Cristina ; Coheur, Luisa (2012) - The work described by Heilman and Smith (2009) should also be mentioned, as they propose a method to rank generated questions, instead of classifying them. Afterwards, we show how question generation is performed depending on the type of learned patterns and we finish with a description of the filters used to discard generated questions of low quality. Keywords: answer; david; impl; mentor; pair; patterns; question; question generation; sculpted; seed; sentence; set; statue; syntactic; text; total

• Referential Communication Between Friends and Strangers in the Wild by Liu, Kris; D'Arcey, J. Trevor; Walker, Marilyn; Fox Tree, Jean (2021) - We chose the number of director descriptors instead of other measures (e.g., number of matcher descriptors) because directors’ descriptors were less subject to cell phone reception problems and because director and matcher descriptors were correlated and therefore similar (see Coding section). Research assistants annotated director descriptors, matcher descriptors, and counted the number of turns taken for each piece of target artwork found. Keywords: acquaintanceship; analysis; communication; descriptors; director; director descriptors; entrainment; extraversion; fox; friends; matcher; number; pairs; participants; research; round; strangers; target; task; tree
• Repair of claimed non-understanding of word meaning in online discussion forum interaction by Myrendal, Jenny (2025) - Abstract This article describes how participants in online discussion forums manage claimed non- understanding of word meaning, specifically when one participant displays insufficient understanding by requesting meta-linguistic clarification. The analysis of these deviant cases reveals the participants’ own normative orientations in repair of claimed non-understanding of word meaning, and thus provide evidence that there is an underlying organization of repair dealing with such issues in online discussion forum interaction. Keywords: analysis; cases; clarification; communication; conversation; det; discussion; excerpt; forum; interaction; meaning; non; online; participants; post; repair; response; sequence; source; study; trouble; turn; understanding; word; word meaning

• Lexical Alignment to Non-native Speakers by Ivanova, Iva; Branigan, Holly; McLean, Janet; Costa, Albert; Pickering, Martin (2021) - Our results from two different language populations suggest that, within the context 166 LEXICAL ALIGNMENT TO NON-NATIVE SPEAKERS of our experiments, audience design led to greater alignment with non-native speakers, but only when communicative success was uncertain (Experiment 1). Together, these results support a role for audience design in alignment to non-native speakers in structured task-based dialogue, but one that is strategically deployed only when deemed necessary. Keywords: alignment; confederate; conversation; design; doi; error; experiment; feedback; group; lexical; names; native; non; order; participants; partner; picture; speakers; type
• German Demonstrative Pronouns in Contrast by Cokal, Derya; Von Heusinger, Klaus (2024) - Given this experimental design, the presence or absence of topic contrast in the previous context would lead to an interaction (all other things being equal) between contrast type and anaphora type, due to the prediction of a difference between (4b) and (4d) and the absence of a contrast effect in (4a) and (4c). However, since the full model did not converge, we reduced the fixed random effect for items and ran the following model instead: Response ~ (1 | subject) + (1|item) + contrast type * anaphora type The intercept was significant (β = 2.27, SE = .258, z = 8.18) and the analysis revealed main effects of anaphora and contrast type (Anaphora: β = -0.366, SE = .180, z = -2.039, p = .041; OR = 0.67, SE = .12, p = .024; Contrast type: β = -0.406, SE = .180, z = -2.249; p = .024; OR = 0.69, SE = .14, p = .041). Keywords: anaphora; cellist; context; contrast; contrast context; demonstrative; der; dieser; discourse; doi; effect; experiment; eye; german; np1; participants; processing; pronouns; reading; region; regressions; schumacher; sentence; studies; topic; type

• Discourse coherence and the interpretation of accented pronouns by Mozuraitis, Mindaugas ; Heller , Daphna (2017) - Pronoun interpretation has been accounted for using the DISCOURSE COHERENCE AND ACCENTED PRONOUNS 85 concept of accessibility (or salience). These kinds of examples have led to the suggestion that pronoun interpretation should not be viewed as a process that operates on referents and their accessibility status alone; instead it should be seen as a by-product of a general mechanism of establishing coherence in discourse (Hobbs, 1978, 1979; Hobbs, Stickel, Appelt, & Martin, 1993; Stevenson, Crawley, & Kleinman, 1994; Stevenson et al., 2000; Kehler, 2002; de Hoop, 2004; Wolf, Gibson, & Desmet, 2004; Jasinskaja, Kölsch, & Mayer, 2007; Kehler, Kertz, Rohde, & Elman, 2008, among others). Keywords: antecedent; coherence; default; discourses; interpretation; object; parallel; pronoun; result; sentence
• Perspective-Taking and Protagonist Prominence: An Empirical Approach to the Role of Local and Global Prominence by Meuser, Sara; Hinterwimmer, Stefan; Hörl, Maximilian (2024) - However, her research focusses on the distinction between speaker/narrator and protagonist perspective without taking into account the possibility that multiple protagonists might be available as perspectival centers. We want to clarify at this point that many utterances in FID mode may receive an objective reading by adding “but he/she was not aware of it”. Keywords: acceptability; center; condition; context; discourse; effect; experiment; expression; fid; hinterwimmer; items; perspective; position; prominence; protagonist; referent; respect; sentence; subject; taking

• Locality in German by Vasishth, Shravan; Drenhaus, Heiner (2011) - An example is the self- paced reading study by Grodner and Gibson (2005), which showed increasing reading time at the verb supervised as a function of the distance between the subject nurse and the verb: (1) a. 65 VASISHTH, AND DRENHAUS 2.4 Discussion We found increased reading times in the critical and post-critical regions as distance between the verb (ignoriert) and the argument (Direktor) is increased. Keywords: distance; effects; expectation; gibson; locality; pass; probability; processing; reading; region; time; vasishth; verb; word
• Processing of discourse anaphors by L2 speakers of English by Cokal, Derya; Sturt, Patrick; Ferreira, Fernanda (2021) - Processing of discourse anaphors by Turkish L2 speakers of English Derya Çokal DCOKAL@QMUL.AC.UK School of Electronic Engineering and Computer Science Queen Mary University of London London, E1 4NS, United Kingdom Patrick Sturt PATRICK.STURT@ED.AC.UK Psychology Department, University of Edinburgh 7 George Square Edinburgh, Midlothian, EH8 9JZ, United Kingdom Fernanda Ferreira FFERREIRA@UCDAVIS.EDU Psychology Department, University of California, Davis 174A Young Hall 1 Shields Avenue Davis, CA 95616 Editor: Jonathan Ginzburg Submitted 09/2020; Accepted 07/2021; Published online 08/2021 In Processing of this and that by Turkish L2 speakers 39 anaphors (e.g., this and that) more extensively than do native speakers (Çokal, 2019; Çokal & Ruhi, 2006; Ellert, 2013; Ferris, 1994; Hinkel, 2001; Jin, 2001; Juvonen, 1996; Niimura & Hayashi, 1996; Wilson, Keller, & Sorace, 2009). Keywords: anaphors; discourse; distal; english; event; experiment; focus; frontier; hours; l2 speakers; learners; line; minutes; new; processing; proximal; reading; referent; speakers; time; turkish; çokal

• Reports in Discourse by Hunter, Julie (2016) - So the difference between discourse parenthetical reports and non-parenthetical reports is that in the latter, the whole report is treated as a single unit that can figure in an argument for a discourse relation whereas in the former, only the embedded content contributes to an argument. The treatment of discourse parenthetical reports in the PDTB, the CDT, and Hunter et al. (2006) all have in common the idea that discourse parenthetical reports are best modelled by attaching the embedded clause directly to the incoming discourse and that this attachment pattern distinguishes them from non-parenthetical reports, in which it is the attribution predicate that is attached to the incoming discourse. Keywords: attribution; clause; commitment; content; discourse; discourse function; discourse parenthetical; discourse relation; discourse structure; discourse unit; hunter; john; parenthetical; predicate; relation; report; semantics; speaker; structure; town

• Clarification and generalized quantifiers by Cooper, Robin (2013) - This separation of the glue function of the λ-calculus and the analysis of quantified utter- ances in terms of generalized quantifier relations between sets leads me to suppose that Purver and Ginzburg’s objection is not so much to generalized quantifiers as such as to the use of Montague’s λ-calculus based approach to compositional semantics. Here the witness and restriction clarifications appear to collapse since a witness set for the quantifier has to be a subset of thieves (i.e. the restriction) which contains most thieves. Keywords: clarification; content; ginzburg; noun; phrase; ppty; purver; quantifier; restriction; scope; set; type; witness
• Demonstrative Pronouns as Anti-Logophoric Pronouns: An Experimental Investigation by Hinterwimmer, Stefan; Brocher, Andreas; Patil, Umesh (2020) - In the first model (see Table 1), where Neutral was the reference level, there were significant main effects of sentence type and pronoun type: Narrator-judgement and FID sentences were judged as more native-like than Neutral sentences, and PPros were judged as more native-like than DPros. Estimates for FID and Narrator-judgement show the effect of these two sentence types with respect to sentences in Neutral type; the estimate for Pronoun type shows the effect of PPro with respect to DPro; and estimates for FID : Pronoun type and Narrator-judgement : Pronoun type show the interaction between FID sentences and the type of the pronoun, and Narrator-judgement sentences and the type of the pronoun. Keywords: bosch; center; conditions; discourse; dpro; fid; hinterwimmer; judgement; narrator; neutral; perspectival; pronouns; referent; respect; sentences; subject; type

• Introduction to the Special Issue on Dialogue State Tracking by Williams, Jason D. ; Raux, Antoine ; Henderson, Matthew (2016) - As conversational systems become a part of daily life – examples include Apple’s Siri, Google Now, and Cortana from Microsoft – interest from the research community in dialog state tracking has grown considerably. Yet to date, work in dialog state tracking has been spread among a number of workshops and conferences. Keywords: challenge; dialog; state; tracking

• Does pre-planning explain why predictability affects reference production? by Zerkle, Sandra A. ; Arnold, Jennifer E. (2019) - Does thematic role predict production planning measures (latency, early looks, and late looks)? Even though latency did not predict reference form choice, eyetracking may provide an earlier and more sensitive measure for identifying planning effects on reference production. Keywords: arnold; discourse; effect; form; goal; latency; looks; planning; predictability; production; reference; reference form; role; rosa; subject; use

• A Uniform Syntax and Discourse Structure: the Copenhagen Dependency Treebanks by Hardt, Daniel (2013) - While the design of the CDT was motivated by the Uniformity Hypothesis, the actual annotation practice has been more flexible, allowing a mechanism for annotating discourse relations in a way that allows for violations of Uniformity. The inventory of discourse relations in CDT is described in the CDT manual. Keywords: cdt; contrast; discourse; relation; says; uniformity

Epilogue

For more detail, about this study carrel, see the computed home page. For more detail about study carrels in general, see the read me file.

Created: 2025-12-23