A Full Data-Driven System for Multiple Language Question Answering
Autor: | Manuel Pérez-Coutiño, Luis Villaseñor-Pineda, Manuel Montes-y-Gómez, Paolo Rosso, Emilio Sanchis-Arnal, José Manuel Gómez-Soriano |
---|---|
Přispěvatelé: | Universidad de Alicante. Departamento de Lenguajes y Sistemas Informáticos, Instituto Nacional de Astrofísica, Óptica y Electrónica (México), Universidad Politécnica de Valencia. Departamento de Sistemas Informáticos y Computación, Procesamiento del Lenguaje Natural y Sistemas de Información, Reconocimiento de Formas e Inteligencia Artificial |
Rok vydání: | 2006 |
Předmět: |
Information extraction
Computer science business.industry computer.software_genre Multilingual Lenguajes y Sistemas Informáticos Information system Question answering Information retrieval Multilingualism Pattern matching Artificial intelligence Adaptation (computer science) business JIRS computer Natural language processing |
Zdroj: | Accessing Multilingual Information Repositories ISBN: 9783540456971 CLEF |
DOI: | 10.1007/11878773_47 |
Popis: | This work is a revised version of the paper “INAOE-UPV Joint Participation at CLEF 2005: Experiments in Monolingual Question Answering”, previously published in the CLEF 2005 working notes (www.clef-campaign.org/2005/working_notes/). This paper describes a full data-driven system for question answering. The system uses pattern matching and statistical techniques to identify the relevant passages as well as the candidate answers for factoid and definition questions. Since it does not consider any sophisticated linguistic analysis of questions and answers, it can be applied to different languages without requiring major adaptation changes. Experimental results on Spanish, Italian and French demonstrate that the proposed approach can be a convenient strategy for monolingual and multilingual question answering. CONACYT (Project Grant 43990); R2D2 (CICYTTIC2003-07158-C04-03); ICT EU-India (ALA/95/23/2003/077-054) |
Databáze: | OpenAIRE |
Externí odkaz: |