Semi-supervised Dependency Parsing using Lexical Affinities

Abstract : 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 pars- ing results on this treebank.
Document type :
Conference papers
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00702486
Contributor : Joseph Le Roux <>
Submitted on : Wednesday, May 30, 2012 - 1:52:37 PM
Last modification on : Thursday, February 7, 2019 - 5:47:51 PM
Long-term archiving on : Thursday, December 15, 2016 - 10:08:18 AM

File

lex_acl2012.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00702486, version 1

Collections

Citation

Seyed Abolghasem Mirroshandel, Alexis Nasr, Joseph Le Roux. Semi-supervised Dependency Parsing using Lexical Affinities. ACL, 2012, South Korea. ⟨hal-00702486⟩

Share

Metrics

Record views

198

Files downloads

142