LIA/LINA at the INEX 2012 Tweet Contextualization track - Laboratoire des Sciences du Numérique de Nantes Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

LIA/LINA at the INEX 2012 Tweet Contextualization track

Romain Deveaud
  • Fonction : Auteur
  • PersonId : 933031
Florian Boudin

Résumé

In this paper we describe our participation in the INEX 2012 Tweet Contextualization track and present our contributions. We combined Information Retrieval, Automatic Summarization and Topic Modeling techniques to provide the context of each tweet. We first formulate a specific query using hashtags and important words in the Tweets to retrieve the most relevant Wikipedia articles. Then, we segment the articles into sentences and compute several measures for each sentence, in order to estimate their contextual relevance to the topics expressed by the Tweets. Finally, the best scored sentences are used to form the context. Official results suggest that our methods performed very well compared to other participants.
Fichier principal
Vignette du fichier
CLEF2012wn-INEX-DeveaudEt2012.pdf (190.35 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00755496 , version 1 (21-11-2012)

Identifiants

  • HAL Id : hal-00755496 , version 1

Citer

Romain Deveaud, Florian Boudin. LIA/LINA at the INEX 2012 Tweet Contextualization track. INitiative for the Evaluation of XML Retrieval (INEX), Sep 2012, Rome, Italy. pp.n/a. ⟨hal-00755496⟩
227 Consultations
126 Téléchargements

Partager

Gmail Facebook X LinkedIn More