Overview of INEX Tweet Contextualization 2013 track - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Overview of INEX Tweet Contextualization 2013 track

Résumé

Twitter is increasingly used for on-line client and audience fishing; this motivated the tweet contextualization task at INEX. The objective is to help a user to understand a tweet by providing him with a short summary (500 words). This summary should be built automatically using local resources like the Wikipedia and generated by extracting relevant passages and aggregating them into a coherent summary. The task is evaluated considering informativeness which is computed using a variant of Kullback-Leibler divergence and passage pooling. Meanwhile effective readability in context of summaries is checked using binary questionnaires on small samples of results. Running since 2010, results show that only systems that efficiently combine passage retrieval, sentence segmentation and scoring, named entity recognition, text POS analysis, anaphora detection, diversity content measure as well as sentence reordering are effective.
Fichier principal
Vignette du fichier
Bellot_13275.pdf (173.42 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01140592 , version 1 (09-04-2015)

Licence

Paternité

Identifiants

  • HAL Id : hal-01140592 , version 1
  • OATAO : 13275

Citer

Patrice Bellot, Véronique Moriceau, Josiane Mothe, Eric Sanjuan, Xavier Tannier. Overview of INEX Tweet Contextualization 2013 track. Conference on Multilingual and Multimodal Information Access Evaluation (CLEF 2013), Sep 2013, Valencia, Spain. pp.1-4. ⟨hal-01140592⟩
572 Consultations
117 Téléchargements

Partager

Gmail Facebook X LinkedIn More