Paper: Parsing the Penn Chinese Treebank with Semantic Knowledge

ACL ID I05-1007
Title Parsing the Penn Chinese Treebank with Semantic Knowledge
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2005
Authors

We build a class-based selection preference sub-model to in- corporate external semantic knowledge from two Chinese electronic se- mantic dictionaries. This sub-model is combined with modifier-head gen- eration sub-model. After being optimized on the held out data by the EM algorithm, our improved parser achieves 79.4% (F1 measure), as well as a 4.4% relative decrease in error rate on the Penn Chinese Treebank (CTB). Further analysis of performance improvement indicates that se- mantic knowledge is helpful for nominal compounds, coordination, and NdiamondmathV tagging disambiguation, as well as alleviating the sparseness of in- formation available in treebank.