DC Field | Value | Language |
---|---|---|
dc.contributor.author | Choi, Keysun | ko |
dc.contributor.author | Park, jungyeul | ko |
dc.contributor.author | Kawahara, Daisuke | ko |
dc.contributor.author | Kurohashi, Sadao | ko |
dc.date.accessioned | 2016-07-13T07:19:30Z | - |
dc.date.available | 2016-07-13T07:19:30Z | - |
dc.date.created | 2016-01-06 | - |
dc.date.created | 2016-01-06 | - |
dc.date.issued | 2013-11-27 | - |
dc.identifier.citation | The 13th International Conference on Parsing Technologies | - |
dc.identifier.uri | http://hdl.handle.net/10203/211477 | - |
dc.description.abstract | We propose a Korean dependency parsing system that can learn the relationships between Korean words from the Treebank corpus and a large raw corpus. We first refine the training dataset to better represent the relationship using a different POS tagging granularity type. We also introduce lexical information and propose an almost fully lexicalized probabilistic model with case frames automatically extracted from a very large raw corpus. We evaluate and compare systems with and without POS granularity refinement and case frames. The proposed lexicalized method outperforms not only the baseline systems but also a state-of-the-art supervised dependency parser. | - |
dc.language | English | - |
dc.publisher | ACL/SIGPARSE | - |
dc.title | Towards Fully Lexicalized Dependency Parsing for Korean | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85096045848 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | The 13th International Conference on Parsing Technologies | - |
dc.identifier.conferencecountry | JA | - |
dc.identifier.conferencelocation | Nara | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Choi, Keysun | - |
dc.contributor.nonIdAuthor | Park, jungyeul | - |
dc.contributor.nonIdAuthor | Kawahara, Daisuke | - |
dc.contributor.nonIdAuthor | Kurohashi, Sadao | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.