Paper: Multi-Tagging For Lexicalized-Grammar Parsing

ACL ID P06-1088
Title Multi-Tagging For Lexicalized-Grammar Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006

Withperformanceabove97%accuracyfor newspaper text, part of speech (POS) tag- ging might be considered a solved prob- lem. Previous studies have shown that allowing the parser to resolve POS tag ambiguity does not improve performance. However, for grammar formalisms which use more fine-grained grammatical cate- gories, for example TAG and CCG, tagging accuracy is much lower. In fact, for these formalisms, premature ambiguity resolu- tion makes parsing infeasible. We describe a multi-tagging approach which maintains a suitable level of lexical category ambiguity for accurate and effi- cient CCG parsing. We extend this multi- tagging approach to the POS level to over- come errors introduced by automatically assigned POS tags. Although POS tagging accuracy seems high, maintaining some POS tag ...