Revisiting knowledge-based Semantic Role Labeling

Quentin Pradet 1, * Gaël de Chalendar 1 Guilhem Pujol 1
* Corresponding author
1 LVIC - Laboratoire Vision et Ingénierie des Contenus
DIASI - Département Intelligence Ambiante et Systèmes Interactifs : DRT/LIST/DIASI
Abstract : Semantic role labeling has seen tremendous progress in the last years, both for supervised and unsupervised approaches. The knowledge-based approaches have been neglected while they have shown to bring the best results to the related word sense disambiguation task. We contribute a simple knowledge-based system with an easy to reproduce specification. We also present a novel approach to handle the passive voice in the context of semantic role labeling that reduces the error rate in F1 by 15.7%, showing that significant improvements can be brought while retaining the key advantages of the approach: a simple approach which facilitates analysis of individual errors, does not need any hand-annotated corpora and which is not domain-specific.
Document type :
Conference papers
Complete list of metadatas

Cited literature [23 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-00932330
Contributor : Quentin Pradet <>
Submitted on : Thursday, January 16, 2014 - 4:56:36 PM
Last modification on : Thursday, February 7, 2019 - 3:04:19 PM
Long-term archiving on : Thursday, April 17, 2014 - 9:49:58 AM

File

2013_LTC.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : cea-00932330, version 1

Collections

CEA | DRT | LIST

Citation

Quentin Pradet, Gaël de Chalendar, Guilhem Pujol. Revisiting knowledge-based Semantic Role Labeling. LTC'13, Dec 2013, Poznań, Poland. pp.71. ⟨cea-00932330⟩

Share

Metrics

Record views

325

Files downloads

462