Skip to Main content Skip to Navigation
Conference papers

Because Syntax does Matter: Improving Predicate-Argument Structures Parsing Using Syntactic Features

Abstract : Parsing full-fledged predicate-argument structures in a deep syntax framework requires graphs to be predicted. Using the DeepBank (Flickinger et al., 2012) and the Predicate-Argument Structure treebank (Miyao and Tsujii, 2005) as a test field, we show how transition-based parsers, extended to handle connected graphs, benefit from the use of topologically different syntactic features such as dependencies, tree fragments, spines or syntactic paths, bringing a much needed context to the parsing models, improving notably over long distance dependencies and elided coordinate structures. By confirming this positive impact on an accurate 2nd-order graph-based parser (Martins and Almeida, 2014), we establish a new state-of-the-art on these data sets.
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01174533
Contributor : Corentin Ribeyre <>
Submitted on : Friday, July 10, 2015 - 4:35:27 PM
Last modification on : Friday, March 27, 2020 - 3:20:01 AM
Document(s) archivé(s) le : Monday, October 12, 2015 - 11:29:23 AM

File

naaclhlt2015.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License

Identifiers

  • HAL Id : hal-01174533, version 1

Citation

Corentin Ribeyre, Éric Villemonte de la Clergerie, Djamé Seddah. Because Syntax does Matter: Improving Predicate-Argument Structures Parsing Using Syntactic Features. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2015, Denver, USA, United States. ⟨hal-01174533⟩

Share

Metrics

Record views

1426

Files downloads

368