4458 articles – 13149 references  [version française]
HAL: hal-00625326, version 1

Short view  Export this paper
Semi-automatic Endogenous Enrichment of Collaboratively Constructed Lexical Resources: Piggybacking onto Wiktionary
Sajous F., Navarro E., Gaume B., Prévot L., Chudy Y.
Dans Advances in Natural Language Processing - 7th International Conference on NLP, IceTAL 2010, Reykjavik : Islande (2010) - http://hal.archives-ouvertes.fr/hal-00625326
Conference proceedings
Humanities and Social Sciences/Linguistics
Computer Science/Computation and Language
Semi-automatic Endogenous Enrichment of Collaboratively Constructed Lexical Resources: Piggybacking onto Wiktionary
Franck Sajous 1, Emmanuel Navarro 2, Bruno Gaume 1, Laurent Prévot 3, Yannick Chudy 1
1:  Cognition, Langues, Langage, Ergonomie (CLLE)
http://w3.univ-tlse2.fr/clle/
CNRS : UMR5263 – Université Michel de Montaigne - Bordeaux III – Université Toulouse le Mirail - Toulouse II – Ecole Pratique des Hautes Etudes
Maison de La Recherche 5 Allées Antonio Machado 31058 TOULOUSE CEDEX 9
France
2:  Institut de recherche en informatique de Toulouse (IRIT)
http://www.irit.fr/
CNRS : UMR5505 – Institut National Polytechnique de Toulouse - INPT – Université des Sciences Sociales - Toulouse I – Université Toulouse I [UT1] Capitole – Université Toulouse le Mirail - Toulouse II – Université Paul Sabatier [UPS] - Toulouse III
118 Route de Narbonne, F-31062 Toulouse Cedex 9
France
3:  Laboratoire Parole et Langage (LPL)
http://www.lpl.univ-aix.fr
CNRS : UMR6057 – Université de Provence - Aix-Marseille I
29 av. R. Schuman - 13621 Aix-en-Provence cedex 1 - France
France
The lack of large-scale, freely available and durable lexical resources, and the consequences for NLP, is widely acknowledged but the attempts to cope with usual bottlenecks preventing their development often result in dead-ends. This article introduces a language-independent, semi-automatic and endogenous method for enriching lexical resources, based on collaborative editing and random walks through existing lexical relationships, and shows how this approach enables us to overcome recurrent impediments. It compares the impact of using different data sources and similarity measures on the task of improving synonymy networks. Finally, it defines an architecture for applying the presented method to Wiktionary and explains how it has been implemented.
English

Advances in Natural Language Processing
international
2010-09-01
6233
332-344
Springer Berlin/Heidelberg
Hrafn Loftsson, Eiríkur Rögnvaldsson and Sigrún Helgadóttir
Lecture Notes in Computer Science

7th International Conference on NLP, IceTAL 2010
2010-08-16
2010-08-18
Reykjavik
Iceland

Collaboratively Constructed Lexical Resources – Endogenous Enrichment – Crowdsourcing – Wiktionary – Random Walks.

Attached file list to this document: 
PDF
sajousEtAl2010-IceTAL.pdf(302.6 KB)