Paper: Acquisition Of Lexical Paraphrases From Texts

ACL ID W02-1411
Title Acquisition Of Lexical Paraphrases From Texts
Venue CompuTerm International Workshop On Computational Terminology
Year 2002
  • Kazuhide Yamamoto (ATR Spoken Language Translation Research Laboratories, Kyoto Japan)

Automatic acquisition of paraphrase knowledge for content words is proposed. Using only a non-parallel text corpus, we compute the para- phrasability metrics between two words from their similarity in context. We then filter words such as proper nouns from external knowledge. Finally, we use a heuristic in further filtering to improve the accuracy of the automatic acqui- sition. In this paper, we report the results of acquisition experiments.