Skip to Main content Skip to Navigation
Conference papers

Discriminative Strategies to Integrate Multiword Expression Recognition and Parsing

Abstract : The integration of multiword expressions in a parsing procedure has been shown to improve accuracy in an artificial context where such expressions have been perfectly pre-identified. This paper evaluates two empirical strategies to integrate multiword units in a real constituency parsing context and shows that the results are not as promising as has sometimes been suggested. Firstly, we show that pre-grouping multiword expressions before parsing with a state-of-the-art recognizer improves multiword recognition accuracy and unlabeled attachment score. However, it has no statistically significant impact in terms of F-score as incorrect multiword expression recognition has important side effects on parsing. Secondly, integrating multiword expressions in the parser grammar followed by a reranker specific to such expressions slightly improves all evaluation metrics.
Document type :
Conference papers
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal-upec-upem.archives-ouvertes.fr/hal-00790613
Contributor : Matthieu Constant <>
Submitted on : Wednesday, February 20, 2013 - 3:42:41 PM
Last modification on : Wednesday, February 26, 2020 - 7:06:06 PM
Long-term archiving on: : Tuesday, May 21, 2013 - 9:26:46 AM

File

constant-sigogne-watrin-vf.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00790613, version 1

Citation

Mathieu Constant, Anthony Sigogne, Patrick Watrin. Discriminative Strategies to Integrate Multiword Expression Recognition and Parsing. 50th Annual Meeting of the Association for Computational Linguistics (ACL'12), Jul 2012, South Korea. pp.204-212. ⟨hal-00790613⟩

Share

Metrics

Record views

280

Files downloads

697