Loading...

Semi-supervised dependency parsing using lexical affinities

Mirroshandel, S. A ; Sharif University of Technology | 2012

363 Viewed
  1. Type of Document: Article
  2. Publisher: 2012
  3. Abstract:
  4. Treebanks are not large enough to reliably model precise lexical phenomena. This deficiency 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% Labeled Accuracy Score yielding the best parsing results on this treebank
  5. Keywords:
  6. Dependency parsing ; Error rate ; Large corpora ; Semi-supervised ; Treebanks ; Computational linguistics ; Forestry
  7. Source: 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference ; Volume 1 , 2012 , Pages 777-785 ; 9781937284244 (ISBN)
  8. URL: http://dl.acm.org/citation.cfm?id=2390524.2390634