Trec Novelty Track At IRIT-SIG
نویسندگان
چکیده
In TREC 2003, IRIT improved the strategy that was introduced in TREC 2002. A sentence is considered as relevant if it matches the topic with a certain level of coverage. This coverage depends on the category of terms used in the texts. Different types of terms have been defined: highly relevant, scarcely relevant, nonrelevant and highly non-relevant. With regard to the novelty part, a sentence is considered as novel if its similarity with previously processed sentences and with the n-best-matching sentences does not exceed certain thresholds.
منابع مشابه
Novelty Track at IRIT-SIG
IRIT developed a new strategy in order to detect the relevant sentences that we did not try in a more general context of document retrieval but did try previously and partially in document categorization. In our approach a sentence is considered as relevant if it matches the topic with a certain level of coverage. This level of coverage depends on the category of the terms used in the texts. Th...
متن کاملIRIT at TREC 2012 Contextual Suggestion Track
In this paper we give an overview of the participation of the IRIT lab, University of Toulouse, France, in the TREC 2012 Contextual Suggestion Track. We present our personalized contextual retrieval framework, an approach for context processing, and two approaches for user preference processing. The official evaluations of our two submitted runs are reported and compared to the four baselines d...
متن کاملIRIT at TREC Microblog 2015
This paper presents the participation of the IRIT laboratory (University of Toulouse) to the Microblog Track of TREC 2015. This track consists in a real-time filtering task aiming at monitoring a stream of social media posts in accordance to a user’s interest profile. In this context, our team proposes three approaches: (a) a novel selective summarization approach based on a decision of selecti...
متن کاملIRIT, GeoComp, and LIUPPA at the TREC 2013 Contextual Suggestion Track
Abstract. In this paper we give an overview of the participation of the IRIT, GeoComp, and LIUPPA labs in the TREC 2013 Contextual Suggestion Track. Our framework combines existing geo-tools or services (e.g., Google Places, Yahoo! BOSS Geo Services, PostGIS, Gisgraphy, GeoNames) and ranks results according to features such as context-place distance, place popularity, and user preferences. We p...
متن کاملIRIT at TREC Microblog Track 2013
This paper describes the participation of the IRIT lab, University of Toulouse, France, to the Microblog Track of TREC 2013. Two different approaches are experimented by our team for the real-time ad-hoc search task: (i) a Bayesian network retrieval model for tweet search and (ii) a document and query expansion model for microblog search.
متن کامل