Conceptual Vectors, a complementary tool to Lexical Networks

Didier Schwab 1 Lim Lian Tze 1 Mathieu Lafourcade 2
2 TEXTE - Exploration et exploitation de données textuelles
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : There is currently much research in natural language processing focusing on lexical networks. Most of them, in particular the most famous, Word- Net, lack syntagmatic information and especially thematic information (”Tennis Problem”). This article describes conceptual vectors that allows the representation of ideas in any textual segment and offers a continuous vision of related thematics, based on the distances between these thematics. We show the characteristics of conceptual vectors and explain how they complement lexico-semantic networks.We illustrate this purpose by adding conceptual vectors toWordNet by emergence.
Document type :
Conference papers
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00200892
Contributor : Mathieu Lafourcade <>
Submitted on : Friday, December 21, 2007 - 5:41:20 PM
Last modification on : Friday, February 15, 2019 - 3:22:03 PM
Long-term archiving on: Tuesday, April 13, 2010 - 3:07:28 PM

Identifiers

  • HAL Id : lirmm-00200892, version 1

Collections

Citation

Didier Schwab, Lim Lian Tze, Mathieu Lafourcade. Conceptual Vectors, a complementary tool to Lexical Networks. NLPCS'07: 4th International Workshop on Natural Language Processing and Cognitive Science, Jun 2007, pp.10. ⟨lirmm-00200892⟩

Share

Metrics

Record views

1044

Files downloads

262