| DOI | Resolve DOI: http://doi.org/10.3115/v1/N15-1065 |
|---|
| Author | Search for: Fujita, Atsushi; Search for: Isabelle, Pierre1 |
|---|
| Name affiliation | - National Research Council Canada. Information and Communication Technologies
|
|---|
| Type | Article |
|---|
| Proceedings title | Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies |
|---|
| Conference | 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, May 31-June 5, 2015, Denver, Colorado, USA |
|---|
| ISBN | 978-1-941643-49-5 |
|---|
| Article number | N15-1065 |
|---|
| Pages | 630–640 |
|---|
| Abstract | This study tackles the problem of paraphrase acquisition: achieving high coverage as well as accuracy. Our method first induces paraphrase patterns from given seed paraphrases, exploiting the generality of paraphrases exhibited by pairs of lexical variants, e.g., “amendment” and “amending,” in a fully empirical way. It then searches monolingual corpora for new paraphrases that match the patterns. This can extract paraphrases comprising words that are completely different from those of the given seeds. In experiments, our method expanded seed sets by factors of 42 to 206, gaining 84% to 208% more coverage than a previous method that generalizes only identical word forms. Human evaluation through a paraphrase substitution test demonstrated that the newly acquired paraphrases retained reasonable quality, given substantially high-quality seeds |
|---|
| Publication date | 2015-05-31 |
|---|
| Publisher | Association for Computational Linguistics |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NPARC number | 23000029 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction |
|---|
Record identifier | 17c01587-4974-485b-916e-e67059fde624 | | Record created | 2016-05-30 |
|---|
| Record modified | 2016-05-30 |
|---|
