Abstract | ||
---|---|---|
This paper presents experiments with WordNet semantic classes to improve dependency parsing. We study the effect of semantic classes in three dependency parsers, using two types of constituency-to-dependency conversions of the English Penn Treebank. Overall, we can say that the improvements are small and not significant using automatic POS tags, contrary to previously published results using gold POS tags (Agirre et al., 2011). In addition, we explore parser combinations, showing that the semantically enhanced parsers yield a small significant gain only on the more semantically oriented LTH treebank conversion. |
Year | Venue | Keywords |
---|---|---|
2014 | PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2 | computational linguistics |
Field | DocType | Volume |
Computer science,Computational linguistics,Dependency grammar,Natural language processing,Treebank,Artificial intelligence,Parsing,Computational lexicology,WordNet,Quantitative linguistics,Language technology | Conference | P14-2 |
Citations | PageRank | References |
2 | 0.37 | 14 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kepa Bengoetxea | 1 | 52 | 5.84 |
Eneko Agirre | 2 | 3119 | 217.33 |
Joakim Nivre | 3 | 3652 | 229.07 |
Yue Zhang | 4 | 1364 | 114.17 |
Koldo Gojenola | 5 | 164 | 26.64 |