Overview of the INEX 2011 Question Answering Track (QA@INEX)

Eric Sanjuan (1) , Véronique Moriceau (2) , Xavier Tannier (2) , Patrice Bellot (3) , Josiane Mothe (4, 5)

1 LIA - Laboratoire Informatique d'Avignon
2 LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur
3 R2I - Recherche d’information et Interactions
4 IRIT-SIG - Systèmes d’Informations Généralisées
5 UT2J - Université Toulouse - Jean Jaurès

The INEX QA track aimed to evaluate complex question-answering tasks where answers are short texts generated from the Wiki-pedia by extraction of relevant short passages and aggregation into a coherent summary. In such a task, Question-answering, XML/passage retrieval and automatic summarization are combined in order to get closer to real information needs. Based on the groundwork carried out in 2009-2010 edition to determine the sub-tasks and a novel evaluation methodology, the 2011 edition experimented contextualizing tweets using a recent cleaned dump of the Wikipedia. Participants had to contextu-alize 132 tweets from the New York Times (NYT). Informativeness of answers has been evaluated, as well as their readability. 13 teams from 6 countries actively participated to this track. This tweet contextualiza-tion task will continue in 2012 as part of the CLEF INEX lab with same methodology and baseline but on a much wider range of tweet types.

Mots clés: Question Answering; Automatic Summarization; Focus In- formation Retrieval; XML; Natural Language Processing; Wikipedia; Text Readability; Text informativeness

Domaines: Informatique et langage [cs.CL]

Eric Sanjuan, Véronique Moriceau, Xavier Tannier, Patrice Bellot, Josiane Mothe. Overview of the INEX 2011 Question Answering Track (QA@INEX). Focused Retrieval of Content and Structure, 10th International Workshop of the Inititative for the Evaluation of XML Retrieval, INEX 2011, pp.188-206, 2012, ⟨10.1007/978-3-642-35734-3_17⟩. ⟨hal-02493676⟩