A Passage Retrieval System for Multilingual Question Answering

Abstract

In this paper we present a new method to improve the coverage of Passage Retrieval (PR) systems when these systems are employed for the Question Answering (QA) tasks. The ranking of passages obtained by the PR system is rearranged to emphasize those passages with more probability to contain the answer. The new ranking is based on finding the n-gram structures of the question that are presented in the passage, and the weight of the passages increases when they contain longer n-grams structures of the question. The results we present show that the application of this method improves notably the coverage of the classical PR system based on the Space Vectorial Model.We would like to thank CONACyT for partially supporting this work under the grant 43990A-1 as well as R2D2 CICYT (TIC2003-07158-C04-03) and ICT EU-India (ALA/95/23/2003/077-054) research projects. 1 http://clef.iei.pi.cnr.it/ V. Matoušek et al. (Eds.): TSD 2005, LNAI 3658, pp. 443-450, 2005. c Springer-Verlag Berlin Heidelberg 2005 444 José Manuel Gómez Soriano et al.

The Role of Lexical Features in Question Answering for Spanish

“…The processing of target documents consists of two parts, first the whole document collection is tagged with MACO [1], gathering the POS tags as well as named entities identification and classification for each document in the collection. The second part of this stage is performed by the JIRS [2] passage retrieval system (PRS), that creates the index for the searching process. The index built by JIRS and the tagged collection are aligned phrase by phrase for each document in the collection.…”

“…A previous evaluation of JIRS [2] shows that the possible answer to a given question is found among the first 20 passages retrieved for over 60% of the training set.…”

Applying Dependency Trees and Term Density for Answer Selection Reinforcement

“…In the second part of the process, and in parallel to the first one, the whole document collection is tagged with the FDG Parser from Conexor, which is based on the Functional Dependency Grammar discussed in [12]. The final part of this step is performed by the JIRS [6] passage retrieval system (PRS), which create the index for the searching process. The index gathered by JIRS and the tagged collection are aligned phrase by phrase for each document in the collection.…”

“…The larger the n-gram structure, the greater the weight of the passage. Details of JIRS metrics can be found in [6]. The second part of the process requires the POS and Parsing tagged forms of each passage in order to gather the representation used to extract candidates answers.…”

Toward an Arabic Question Answering System over Linked Data

“…Research in QA received a big surge in interest when a shared task on factoid QA was included in the 8 th Text REtrieval Conference (TREC) [19]. Most systems process textual information, such as Youzheng et al [20], Mulder [21], PALANTIR [22], QALC [23], Gómez et al [24], Ryu et al [25]. These question answering systems can be divided into three main distinct subtasks [26]- [28], which are Question Analysis, Document Retrieval and Answer Extraction.…”