Show simple item record

dc.contributor.advisorBender, Emilyen_US
dc.contributor.authorPozen, Zinaidaen_US
dc.date.accessioned2013-07-25T17:51:15Z
dc.date.available2013-07-25T17:51:15Z
dc.date.issued2013-07-25
dc.date.submitted2013en_US
dc.identifier.otherPozen_washington_0250O_11580.pdfen_US
dc.identifier.urihttp://hdl.handle.net/1773/23469
dc.descriptionThesis (Master's)--University of Washington, 2013en_US
dc.description.abstractAccurate parse ranking is essential for deep linguistic processing applications and is one of the classic problems for academic research in NLP. Despite significant advances, there remains a big need for improvement, especially for domains where gold-standard training data is scarce or unavailable. An overwhelming majority of parse ranking methods today rely on modeling syntactic derivation trees. At the same time, parsers that output semantic representations in addition to syntactic derivations (like the monostratal DELPH-IN HPSG parsers) offer an alternative structure for training the ranking model, which could be further combined with the baseline syntactic model score for re-ranking. This thesis proposes a method for ranking the semantic sentence representations, taking advantage of compositional and lexical semantics. The methodology does not require sense-disambiguated data, and therefore can be adopted without requiring a solution for word sense disambiguation. The approach was evaluated in the context of HPSG parse disambiguation for two different domains, as well as in a cross-domain setting, yielding relative error rate reduction of 11.36% for top-10 parse selection compared to the baseline syntactic derivation-based parse ranking model, and a standalone ranking accuracy approaching the accuracy of the baseline syntactic model in the best setup.en_US
dc.format.mimetypeapplication/pdfen_US
dc.language.isoen_USen_US
dc.rightsCopyright is held by the individual authors.en_US
dc.subjectComputational Linguistics; Natural Language Processingen_US
dc.subject.otherLinguisticsen_US
dc.subject.otherlinguisticsen_US
dc.titleUsing Lexical and Compositional Semantics to Improve HPSG Parse Selectionen_US
dc.typeThesisen_US
dc.embargo.termsNo embargoen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record