Abstract
Recent research suggests that sentence structure can improve the accuracy of recognizing textual entailments and paraphrasing. Although background knowledge such as gazetteers, WordNet and custom built knowledge bases are also likely to improve performance, our goal in this paper is to characterize the syntactic features alone that aid in accurate entailment prediction. We describe candidate features, the role of machine learning, and two final decision rules. These rules resulted in an accuracy of 60.50 and 65.87% and average precision of 58.97 and 60.96% in RTE3Test and suggest that sentence structure alone can improve entailment accuracy by 9.25 to 14.62% over the baseline majority class.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 101-106 |
| Number of pages | 6 |
| Journal | Proceedings of the Annual Meeting of the Association for Computational Linguistics |
| State | Published - 2007 |
| Externally published | Yes |
| Event | 2007 ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, ACL-PASCAL 2007 at the Annual Meeting of the Association for Computational Linguistics, ACL 2007 - Prague, Czech Republic Duration: Jun 28 2007 → Jun 29 2007 |
ASJC Scopus subject areas
- Computer Science Applications
- Linguistics and Language
- Language and Linguistics