id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
dad-13359	Walker, Nicholas Thomas; Ultes, Stefan; Lison, Pierre	A Graph-to-Text Approach to Knowledge-Grounded Response Generation in Human–Robot Interaction	2025	36	.pdf	application/pdf	17146	927	47	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.	cache/dad-13359.pdf	txt/dad-13359.txt
