Two Approaches for Multilingual Question Answering: Merging Passages vs. Merging Answers

Computational Linguistics and Chinese Language Processing Vol. 13, No. 1, March 2008, pp. 27-40 27 © The Association for Computational Linguistics and Chinese Language Processing [Received June 30, 2007; Revised October 8, 2007; Accepted January 12, 2008] Two Approaches for Multilingual Question Answering: Merging Passages vs. Merging Answers Rita M. Aceves-Pérez∗, Manuel Montes-y-Gómez∗, Luis Villaseñor-Pineda∗, and L. Alfonso Ureña-López+ Abstract One major problem in multilingual Question Answering (QA) is the integration of information obtained from different languages into one single ranked list. This paper proposes two different architectures to overcome this problem. The first one performs the information merging at passage level, whereas the second does it at answer level. In both cases, we applied a set of traditional merging strategies from cross-lingual information retrieval. Experimental results evidence the appropriateness of these merging strategies for the task of multilingual QA, as well as the advantages of multilingual QA over the traditional monolingual approach. Keywords: Multilingual Question Answering, Cross-Lingual Information Retrieval, Information Merging. 1. Introduction Question Answering (QA) has become a promising research field whose aim is to provide more natural access to textual information than traditional document retrieval techniques [Laurent et al. 2006]. In essence, a QA system is a kind of search engine that responds to natural language questions with concise and precise answers. For instance, given the question “Where is the Popocatepetl Volcano located?”, a QA system has to respond “Mexico”, instead of returning a list of related documents to the volcano. ∗ Laboratory of Language Technologies, National Institute of Astrophysics, Optics and Electronics (INAOE). Luis Enrique Erro #1, Sta. María Tonantzintla, Puebla, Mexico. Tel.: +52-222-2663100 ext: 8218 Fax: +52-222-2663152. The author for correspondence is Manuel Montes-y-Gómez. Email: mmontesg@inaoep.mx + Department of Computer Science, University of Jaén. Campus Las Lagunillas s/n, Edif D3, Jaén, Spain 28 Rita M. Aceves-Pérez et al. At present, due to the internet explosion and the existence of several multicultural communities, one of the major challenges to face this kind of system is multilinguality. In a multilingual scenario, it is expected that QA systems will be able to: (i) answer questions formulated in several languages, and (ii) look for answers in a number of collections in different languages. There are two recognizable kinds of QA systems that allow management of information in various languages: cross-lingual QA systems and, strictly speaking, multilingual QA systems. The former addresses a situation where questions are formulated in a different language from that of the (single) document collection. The other, in contrast, performs the search over two or more document collections in different languages. It is important to mention that both kinds of systems have some advantages over standard monolingual QA. They mainly allow users to access more information in an easier and faster way than monolingual systems. However, they also introduce additional issues due to the language barrier. Generally speaking, a multilingual QA system can be described as an ensemble of several monolingual systems, where each one works on a different – monolingual – document collection. Under this …

Content truncated to 500 words