Towards Answer Extraction: An application to Technical Domains

Towards Answer Extraction: An application to Technical Domains

inproceedings
Fabio Rinaldi, J Dowdall, M Hess, D MollĆ  Aliod, R Schwitter
Frank van Harmelen
The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research com- munity towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extrac- tion (AE) systems aim to satisfy this need. This paper presents one such system (ExtrAns) which works by transforming documents and queries into a semantic representation called Minimal Logical Form (MLF) and derives the answers by logical proof from the documents. MLFs use underspeciļ¬cation to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.
Towards Answer Extraction: An application to Technical Domains
2002
ECAI 2002. Proceedings of the 15th European Conference on Artificial Intelligence
Amsterdam, Netherlands