Paper: A Simple Approach for HPSG Supertagging Using Dependency Information

ACL ID N10-1090
Title A Simple Approach for HPSG Supertagging Using Dependency Information
Venue Human Language Technologies
Session Main Conference
Year 2010
Authors

In a supertagging task, sequence labeling models are commonly used. But their lim- ited ability to model long-distance informa- tion presents a bottleneck to make further im- provements. In this paper, we modeled this long-distance information in dependency for- malism and integrated it into the process of HPSG supertagging. Theexperimentsshowed that the dependency information is very in- formative for supertag disambiguation. We also evaluatedtheimprovedsupertaggerin the HPSG parser.