Exploiting redundancy in question answering
Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Scaling question answering to the web
ACM Transactions on Information Systems (TOIS)
Complex answers: a case study using a WWW question answering system
Natural Language Engineering
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
In question answering, two heads are better than one
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Numerical data integration for cooperative question-answering
KRAQ '06 Proceedings of the Workshop KRAQ'06 on Knowledge and Reasoning for Language Processing
From symbolic to sub-symbolic information in question classification
Artificial Intelligence Review
Hi-index | 0.00 |
A usual strategy to select the final answer in factoid Question-Answering (QA) relies on redundancy. A score is given to each candidate answer as a function of its frequency of occurrence, and the final answer is selected from the set of candidates sorted in decreasing order of score. For that purpose, systems often try to group together semantically equivalent answers. However, they hold several other semantic relations, such as inclusion, which are not considered, and candidates are mostly seen independently, as competitors. Our hypothesis is that not just equivalence, but other relations between candidate answers have impact on the performance of a redundancy-based QA system. In this paper, we describe experimental studies to back up this hypothesis. Our findings show that, with relatively simple techniques to recognize relations, systems' accuracy can be improved for answers of categories NUMBER, DATE and ENTITY.