@inproceedings{mihalcea2006corpus,
abstract = {This paper presents a method for measuring the semantic similarity of texts, using corpus-based and knowledge-based measures of similarity. Previous work on this problem has focused mainly on either large documents (e.g. text classification, information retrieval) or individual words (e.g. synonymy tests). Given that a large fraction of the information available today, on the Web and elsewhere, consists of short text snippets (e.g. abstracts of scientific documents, imagine captions, product descriptions), in this paper we focus on measuring the semantic similarity of short texts. Through experiments performed on a paraphrase data set, we show that the semantic similarity method out-performs methods based on simple lexical matching, resulting in up to 13\% error rate reduction with respect to the traditional vector-based similarity metric.},
author = {Mihalcea, Rada and Corley, Courtney and Strapparava, Carlo},
booktitle = {AAAI},
keywords = {SML-LIB-BIBLIO,lang:ENG},
mendeley-tags = {SML-LIB-BIBLIO,lang:ENG},
pages = {775--780},
title = {{Corpus-based and knowledge-based measures of text semantic similarity}},
volume = {6},
year = {2006}
}