Learning Reliable Information for Dependency Parsing Adaptation

In this paper, we focus on the adaptation problem that has a large labeled data in the source domain and a large but unlabeled data in the target domain. Our aim is to learn reliable information from unlabeled target domain data for dependency parsing adaptation. Current state-of-the-art statistical parsers perform much better for shorter dependencies than for longer ones. Thus we propose an adaptation approach by learning reliable information on shorter dependencies in an unlabeled target data to help parse longer distance words. The unlabeled data is parsed by a dependency parser trained on labeled source domain data. The experimental results indicate that our proposed approach outperforms the baseline system, and is better than current state-of-the-art adaptation techniques.

• Type: Conference
• Year: 2008
• Where: COLING
• Authors: Wenliang Chen, Youzheng Wu, Hitoshi Isahara
• Keywords: COLING 2008, Computational Linguistics, Unlabeled Data, Unlabeled Target, Unlabeled Target Domain