id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_5btix32qbfgvriqhr7d64hs5mq	Gabriella Lapesa	A Large Scale Evaluation of Distributional Semantic Models: Parameters, Interactions and Model Selection	2014	16	.pdf	application/pdf	9457	1020	64	evaluation study of window-based Distributional Semantic Models on a wide variety of show that our strategy allows us to identify parameter configurations that achieve good performance across different datasets and tasks1. goal: it presents the results of a large-scale evaluation of window-based DSMs on a wide variety of semantic tasks. Bullinaria and Levy (2007) report on a systematic study of the impact of a number of parameters (shape and size of the co-occurrence window, corpus, and evaluated on a number of tasks (including TOEFL and noun clustering on the dataset of corpus, window size, number of context dimensions, use of stemming, lemmatization and stopwords, similarity metric, score for feature weighting. Our study aims at extending their parameter set and evaluation methodology to standard tasks. Comparative clustering experiments showed no substantial differences for cosine similarity; in the rank-based setting, pam consistently outperformed	./cache/work_5btix32qbfgvriqhr7d64hs5mq.pdf	./txt/work_5btix32qbfgvriqhr7d64hs5mq.txt