Paraphrase Alignment for Synonym Evidence Discovery

We describe a new unsupervised approach for synonymy discovery by aligning paraphrases in monolingual domain corpora. For that purpose, we identify phrasal terms that convey most of the concepts within domains and adapt a methodology for the automatic extraction and alignment of paraphrases to identify paraphrase casts from which valid synonyms are discovered. Results performed on two different domain corpora show that general synonyms as well as synonymic expressions can be identified with a 67.27% precision.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Gintare Grigonyte, João Cordeiro, Gaël Dias, Rumen Moraliyski, Pavel Brazdil
• Keywords: COLING 2010, Computational Linguistics, Domain Corpora, Monolingual Domain Corpora, Paraphrase