IRIT at INEX 2014 : Tweet Contextualization Track - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

IRIT at INEX 2014 : Tweet Contextualization Track

Abstract

The paper presents IRIT's approach used at INEX Tweet Contextualization Track 2014. Systems had to provide a context to a tweet from the perspective of the entity. This year we further modified our approach presented at INEX 2011, 2012 and 2013 underlain by the product of different measures based on smoothing from local context, named entity recognition, part-ofspeech weighting and sentence quality analysis. We introduced two ways to link an entity and a tweet, namely (1) concatenation of the entity and the tweet and (2) usage of the results obtained for the entity as a restriction to filter results retrieved for the tweet. Besides, we examined the influence of topic-comment relationship on contextualization.
Fichier principal
Vignette du fichier
ermakova_13277.pdf (227.91 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01156597 , version 1 (27-05-2015)

Identifiers

  • HAL Id : hal-01156597 , version 1
  • OATAO : 13277

Cite

Liana Ermakova, Josiane Mothe. IRIT at INEX 2014 : Tweet Contextualization Track. CLEF 2014 - Conference on Multilingual and Multimodal Information Access Evaluation, Sep 2014, Sheffield, United Kingdom. pp.0. ⟨hal-01156597⟩
118 View
26 Download

Share

Gmail Facebook X LinkedIn More