Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and French

Abstract : We present an architecture for parsing in two steps. A phrase-structure parser builds for each sentence an n-best list of analyses which are converted to dependency trees. These de- pendency structures are then rescored by a dis- criminative reranker. Our method is language agnostic and enables the incorporation of ad- ditional information which are useful for the choice of the best parse candidate. We test our approach on the the Penn Treebank and the French Treebank. Evaluation shows a sig- nificative improvement on different parse met- rics.
Document type :
Conference papers
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00702499
Contributor : Joseph Le Roux <>
Submitted on : Wednesday, May 30, 2012 - 2:17:50 PM
Last modification on : Thursday, February 7, 2019 - 5:53:08 PM
Long-term archiving on : Thursday, December 15, 2016 - 10:24:24 AM

File

reranking.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00702499, version 1

Collections

Citation

Joseph Le Roux, Benoit Favre, Alexis Nasr, Seyed Abolghasem Mirroshandel. Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and French. ACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing of Morphologically Rich Languages (SP-Sem-MRL 2012), 2012, South Korea. ⟨hal-00702499⟩

Share

Metrics

Record views

201

Files downloads

282