Increasing Long Tail in Weighted Lexical Networks

Mathieu Lafourcade 1 Alain Joubert 1
1 TEXTE - Exploration et exploitation de données textuelles
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : Lexical networks can be used with benefit for semantic analysis of texts, word sense disambiguation (WSD) and in general for graph-based Natural Language Processing. Usually strong relations between terms (e.g.: cat --> animal) are sufficient to help for the task, but quite often, weak relations (e.g.: cat --> ball of wool) are necessary. Our purpose here is to acquire such relations by means of online serious games as other classical approaches seems impractical. Indeed, it is difficult to ask the users (non experts) to define a proper weighting for the relations they propose, and then we decided to relate weights with the frequency of their propositions. It allows us to acquire first the strongest relations, but also to populate the long tail of an already existing network. Furthermore, trying to get an estimation of our network by the very users thanks to a tip of the tongue (TOT) software, we realized that they rather tend to favor the relations of the long tail and thus promote their emergence. Developing the long tail of a lexical network with standard and non-standard relations of low weight can be of advantage for tasks such that words retrieval from clues or WSD in texts.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00816236
Contributor : Mathieu Lafourcade <>
Submitted on : Saturday, April 20, 2013 - 10:44:51 PM
Last modification on : Friday, February 15, 2019 - 3:22:03 PM
Long-term archiving on: Sunday, July 21, 2013 - 4:07:55 AM

File

COGALEX2012-ML-v4.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-00816236, version 1

Collections

Citation

Mathieu Lafourcade, Alain Joubert. Increasing Long Tail in Weighted Lexical Networks. Cognitive Aspects of the Lexicon (CogAlex-III), COLING, France. pp.16. ⟨lirmm-00816236⟩

Share

Metrics

Record views

1100

Files downloads

387