Paraphrase Substitution for Recognizing Textual Entailment
| Autor: | Bosma, W.E., Callison-Burch, C., Peters, C., Clough, P., Gey, F.C., Karlgren, J., Magnini, B., Oard, D.W., de Rijke, M., Stempfhuber, M. |
|---|---|
| Rok vydání: | 2007 |
| Předmět: |
Matching (statistics)
Computer science business.industry Speech recognition Substitution (logic) computer.software_genre Paraphrase Longest common subsequence problem EWI-11353 HMI-SLT: Speech and Language Technology Artificial intelligence Textual entailment business METIS-245759 computer IR-64445 Word (computer architecture) Natural language processing |
| Zdroj: | Evaluation of Multilingual and Multi-modal Information Retrieval ISBN: 9783540749981 CLEF (Working Notes) Evaluation of Multilingual and Multi-modal Information Retrieval, 502-509 STARTPAGE=502;ENDPAGE=509;TITLE=Evaluation of Multilingual and Multi-modal Information Retrieval |
| ISSN: | 0302-9743 |
| Popis: | We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a flexible match using automatically generated paraphrases. We find that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|