Paper: Semi-supervised Dependency Parsing using Lexical Affinities

ACL ID P12-1082
Title Semi-supervised Dependency Parsing using Lexical Affinities
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

Treebanks are not large enough to reliably model precise lexical phenomena. This de- ficiency provokes attachment errors in the parsers trained on such data. We propose in this paper to compute lexical affinities, on large corpora, for specific lexico-syntactic configurations that are hard to disambiguate and introduce the new information in a parser. Experiments on the French Treebank showed a relative decrease of the error rate of 7.1% La- beled Accuracy Score yielding the best pars- ing results on this treebank.