Learn More
RÉSUMÉ La campagne Défi de Fouille de Textes (DEFT) en 2013 s'est intéressée à deux types de fonctions d'analyse du langage, la classification de documents et l'extraction d'information dans le domaine de spécialité des recettes de cuisine. Nous présen-tons les systèmes du LIA appliqués à DEFT 2013. Malgré la difficulté des tâches proposées, des résultats(More)
Modern popular TV series often develop complex storylines spanning several seasons, but are usually watched in quite a discontinuous way. As a result, the viewer generally needs a comprehensive summary of the previous season plot before the new one starts. The generation of such summaries requires first to identify and characterize the dynamics of the(More)
Speaker diarization may be difficult to achieve when applied to narrative films, where speakers usually talk in adverse acoustic conditions: background music, sound effects, wide variations in intonation may hide the inter-speaker variability and make audio-based speaker diarization approaches error prone. On the other hand, such fictional movies exhibit(More)
Twitter is now a gold marketing tool for entities concerned with online reputation. To automatically monitor online reputation of entities , systems have to deal with ambiguous entity names, polarity detection and topic detection. We propose three approaches to tackle the first issue: monitoring Twitter in order to find relevant tweets about a given entity.(More)
RÉSUMÉ. La segmentation de flux audio en locuteurs apparaît particulièrement délicate lors-qu'elle est appliquée à des films de fiction, où de nombreux personnages parlent dans des conditions acoustiques variables (musique de fond, bruitages, fluctuations dans l'intonation...). Au-delà d'une telle variabilité acoustique, ce type de films exhibe cependant de(More)
In this paper , we present the participation of the Computer Science Laboratory of Avignon (LIA) to RepLab 2013 edition. RepLab is an evaluation campaign for Online Reputation Management Systems. LIA has produced a important number of experiments for every tasks of the campaign : filtering , topic priority detection , Polarity for Reputation and topic(More)