Skip to Main content Skip to Navigation
Conference papers

Statistical French dependency parsing: treebank conversion and first results

Abstract : We first describe the automatic conversion of the French Treebank (Abeillé and Barrier, 2004), a constituency treebank, into typed projective dependency trees. In order to evaluate the overall quality of the resulting dependency treebank, and to quantify the cases where the projectivity constraint leads to wrong dependencies, we compare a subset of the converted treebank to manually validated dependency trees. We then compare the performance of two treebank-trained parsers that output typed dependency parses. The first parser is the MST parser (McDonald et al., 2006), which we directly train on dependency trees. The second parser is a combination of the Berkeley parser (Petrov et al., 2006) and a functional role labeler: trained on the original constituency treebank, the Berkeley parser first outputs constituency trees, which are then labeled with functional roles, and then converted into dependency trees. We found that used in combination with a high-accuracy French POS tagger, the MST parser performs a little better for unlabeled dependencies (UAS=90.3% versus 89.6%), and better for labeled dependencies (LAS=87.6% versus 85.6%).
Complete list of metadatas

Cited literature [28 references]  Display  Hide  Download
Contributor : Marie Candito <>
Submitted on : Tuesday, September 7, 2010 - 3:47:21 PM
Last modification on : Friday, March 27, 2020 - 2:55:48 AM
Document(s) archivé(s) le : Wednesday, December 8, 2010 - 2:24:50 AM


Files produced by the author(s)


  • HAL Id : hal-00495196, version 1



Marie Candito, Benoît Crabbé, Pascal Denis. Statistical French dependency parsing: treebank conversion and first results. Seventh International Conference on Language Resources and Evaluation - LREC 2010, May 2010, La Valletta, Malta. pp.1840-1847. ⟨hal-00495196⟩



Record views


Files downloads