Paper: Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain Data

ACL ID P13-2104
Title Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain Data
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

In this paper, we propose a simple and effective approach to domain adaptation for dependency parsing. This is a fea- ture augmentation approach in which the new features are constructed based on sub- tree information extracted from the auto- parsed target domain data. To demon- strate the effectiveness of the proposed ap- proach, we evaluate it on three pairs of source-target data, compared with sever- al common baseline systems and previous approaches. Our approach achieves signif- icant improvement on all the three pairs of data sets.