LIA/LINA at the INEX 2012 Tweet Contextualization track

In this paper we describe our participation in the INEX 2012 Tweet Contextualization track and present our contributions. We com- bined Information Retrieval, Automatic Summarization and Topic Mod- eling techniques to provide the context of each tweet. We rst formulate a specic query using hashtags and important words in the Tweets to retrieve the most relevant Wikipedia articles. Then, we segment the ar- ticles 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. Ocial results suggest that our methods performed very well compared to other participants.