Paper: Evaluating Impact of Re-training a Lexical Disambiguation Model on Domain Adaptation of an HPSG Parser

ACL ID W07-2202
Title Evaluating Impact of Re-training a Lexical Disambiguation Model on Domain Adaptation of an HPSG Parser
Venue Conference on Parsing Technologies
Session Main Conference
Year 2007
Authors

This paper describes an effective approach to adapting an HPSG parser trained on the Penn Treebank to a biomedical domain. In this approach, we train probabilities of lex- ical entry assignments to words in a tar- get domain and then incorporate them into the original parser. Experimental results show that this method can obtain higher parsing accuracy than previous work on do- main adaptation for parsing the same data. Moreover, the results show that the combi- nation of the proposed method and the exist- ing method achieves parsing accuracy that is as high as that of an HPSG parser retrained from scratch, but with much lower training cost. We also evaluated our method in the Brown corpus to show the portability of our approach in another domain.