Skip to Main content Skip to Navigation
Conference papers

A Transition-Based System for Joint Lexical and Syntactic Analysis

Abstract : We present a transition-based system that jointly predicts the syntactic structure and lexical units of a sentence by building two structures over the input words: a syntactic dependency tree and a forest of lexical units including multiword expressions (MWEs). This combined representation allows us to capture both the syntactic and semantic structure of MWEs, which in turn enables deeper downstream semantic analysis, especially for semi-compositional MWEs. The proposed system extends the arc-standard transition system for dependency parsing with transitions for building complex lexical units. Experiments on two different data sets show that the approach significantly improves MWE identification accuracy (and sometimes syntactic accuracy) compared to existing joint approaches.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01808689
Contributor : Constant Mathieu <>
Submitted on : Tuesday, June 5, 2018 - 11:19:48 PM
Last modification on : Friday, March 27, 2020 - 3:51:35 AM
Document(s) archivé(s) le : Thursday, September 6, 2018 - 6:30:37 PM

File

transition-based-system.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01808689, version 1

Citation

Mathieu Constant, Joakim Nivre. A Transition-Based System for Joint Lexical and Syntactic Analysis. 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), Aug 2016, Berlin, Germany. pp.161 - 171. ⟨hal-01808689⟩

Share

Metrics

Record views

136

Files downloads

229