Towards a multilingual QA system based on the web data redundancy

Authors:
Rita Aceves-Pérez;Luis Villaseñor-Pineda;Manuel Montes-y-Gomez
Affiliations:
Language Technologies Group, Computer Science Department, National Institute of Astrophysics, Optics and Electronics (INAOE), Mexico;Language Technologies Group, Computer Science Department, National Institute of Astrophysics, Optics and Electronics (INAOE), Mexico;Language Technologies Group, Computer Science Department, National Institute of Astrophysics, Optics and Electronics (INAOE), Mexico
Venue:
AWIC'05 Proceedings of the Third international conference on Advances in Web Intelligence
Year:
2005

Citing 1
Cited 4

QA on the Web: A Preliminary Study for Spanish Language

ENC '04 Proceedings of the Fifth Mexican International Conference in Computer Science

Improving the performance of question answering with semantically equivalent answer patterns

Data & Knowledge Engineering
Answering questions with an n-gram based passage retrieval engine

Journal of Intelligent Information Systems
Automatic acquisition of semantic-based question reformulations for question answering

CICLing'06 Proceedings of the 7th international conference on Computational Linguistics and Intelligent Text Processing
Using semantic constraints to improve question answering

NLDB'06 Proceedings of the 11th international conference on Applications of Natural Language to Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper explores the feasibility of a multilingual question answering approach based on the Web redundancy. The paper introduces a system prototype that combines a translation machine with a statistical QA method. The main advantage of this proposal is its small dependence to a given language. The experimental results, obtained from a test set of 165 factual questions, demostrated the great potential of the approach, and gave interesting insights about the redundancy of the web and the online translators.