Abstract
We present a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1%, an absolute 1.1% improvement (12% error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon.
Original language | English |
---|---|
Title of host publication | HLT-NAACL 2006 - Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings of the Main Conference |
Editors | Robert C. Moore, Jeff A. Bilmes, Jennifer Chu-Carroll, Mark Sanderson |
Place of Publication | East Stroudsburg, PA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 152-159 |
Number of pages | 8 |
ISBN (Electronic) | 9781932432626 |
DOIs | |
Publication status | Published - 2006 |
Externally published | Yes |
Event | 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 - New York, NY, United States Duration: 4 Jun 2006 → 9 Jun 2006 |
Other
Other | 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 |
---|---|
Country/Territory | United States |
City | New York, NY |
Period | 4/06/06 → 9/06/06 |