id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
american_scientific_journal-2088	Myint, Zun May; Tun, Phyo Thuzar	Semantic Based Information Retrieval System Using Modified Inverse Document Frequency	2016	14	.pdf	application/pdf	4475	200	50	[clustering] clustering Training vector 1 for sense 1 [density, based, method, discovers, clusters, spatial, database] Training vector 2 for sense 2 [density, method, based, density, distribution, functions] Testing vector [density] The KNN classifier, cosine similarity and TF-IDF method are used to search the most relevant sense of each ambiguous word by classifying each training vector and testing vector. The rest of the paper is organized as follows: Section 2 describes the explanation of the system with the original TF-IDF method, modified TF-IDF method and experimental results.	cache/american_scientific_journal-2088.pdf	txt/american_scientific_journal-2088.txt