Enriching the output of a parser using memory-based learning
| Authors |
|
| Publication date |
2004
|
| Book title |
Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL 2004)
|
| Pages (from-to) |
311-318
|
| Organisations |
-
Faculty of Science (FNWI) - Informatics Institute (IVI)
|
| Abstract |
We describe a method for enriching the output of aparser with information available in a corpus. Themethod is based on graph rewriting using memorybasedlearning, applied to dependency structures.This general framework allows us to accurately recoverboth grammatical and semantic informationas well as non-local dependencies. It also facilitatesdependency-based evaluation of phrase structureparsers. Our method is largely independent ofthe choice of parser and corpus, and shows state ofthe art performance.
|
| Document type |
Chapter
|
|
Permalink to this page
|
Back
