Research output per year
Research output per year
Sunghwan Mac Kim*, Dominick Ng, Mark Johnson, James R. Curran
Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review
This paper presents a novel method of improving Combinatory Categorial Grammar (CCG) parsing using features generated from Dependency Grammar (DG) parses and combined using reranking. Different grammar formalisms have different strengths and different parsing models have consequently divergent views of the data. More specifically, dependency parsers are sensitive to linguistic generalisations that differ from the generalisations that the CCG parser is sensitive to, and which the reranker exploits to identify the parse most likely to be correct. We propose DG-derived reranking features, which are obtained by comparing dependencies from the CCG parser with DG dependencies, and demonstrate how they improve the performance of a CCG parser and reranker in a variety of settings. We record a final labeled F-score of 87.93% on section 23 of CCGbank, 0.5% and 0.35% improvements over the base parser (87.43%) and reranker (87.58%), respectively.
Original language | English |
---|---|
Title of host publication | 24th International Conference on Computational Linguistics |
Subtitle of host publication | Proceedings of COLING 2012: Technical Papers |
Editors | Martin Kay, Christian Boitet |
Place of Publication | Mumbai |
Publisher | Indian Institute of Technology |
Pages | 1441-1458 |
Number of pages | 18 |
Publication status | Published - 2012 |
Event | 24th International Conference on Computational Linguistics, COLING 2012 - Mumbai, India Duration: 8 Dec 2012 → 15 Dec 2012 |
Other | 24th International Conference on Computational Linguistics, COLING 2012 |
---|---|
Country/Territory | India |
City | Mumbai |
Period | 8/12/12 → 15/12/12 |
Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review
Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review