Self-training for enhancement and domain adaptation of statistical parsers trained on small datasets

Roi Reichart*, Ari Rappoport

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

75 Scopus citations

Abstract

Creating large amounts of annotated data to train statistical PCFG parsers is expensive, and the performance of such parsers declines when training and test data are taken from different domains. In this paper we use selftraining in order to improve the quality of a parser and to adapt it to a different domain, using only small amounts of manually annotated seed data. We report significant improvement both when the seed and test data are in the same domain and in the out-of-domain adaptation scenario. In particular, we achieve 50% reduction in annotation cost for the in-domain case, yielding an improvement of 66%over previous work, and a 20-33% reduction for the domain adaptation case. This is the first time that self-training with small labeled datasets is applied successfully to these tasks. We were also able to formulate a characterization of when selftraining is valuable.

Original languageAmerican English
Title of host publicationACL 2007 - Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics
Pages616-623
Number of pages8
StatePublished - 2007
Event45th Annual Meeting of the Association for Computational Linguistics, ACL 2007 - Prague, Czech Republic
Duration: 23 Jun 200730 Jun 2007

Publication series

NameACL 2007 - Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics

Conference

Conference45th Annual Meeting of the Association for Computational Linguistics, ACL 2007
Country/TerritoryCzech Republic
CityPrague
Period23/06/0730/06/07

Fingerprint

Dive into the research topics of 'Self-training for enhancement and domain adaptation of statistical parsers trained on small datasets'. Together they form a unique fingerprint.

Cite this