WordNet: a lexical database for English
Communications of the ACM
Building a question answering test collection
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Dialogue Management for Interactive Question Answering
Proceedings of the Fourteenth International Florida Artificial Intelligence Research Society Conference
Using Prior Knowledge: Problems and Solutions
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Generating natural language summaries from multiple on-line sources
Computational Linguistics - Special issue on natural language generation
A question answering system supported by information extraction
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
A new statistical parser based on bigram lexical dependencies
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Experiments with open-domain textual Question Answering
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
The structure and performance of an open-domain question answering system
ACL '00 Proceedings of the 38th Annual Meeting on Association for Computational Linguistics
Answer Extraction in Technical Domains
CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
Natural Language Engineering
Knowledge element extraction for knowledge-based learning resources organization
ICWL'07 Proceedings of the 6th international conference on Advances in web based learning
Hi-index | 0.00 |
Mining the answer of a natural language open-domain question in a large collection of on-line documents is made possible by the recognition of the expected answer type in relevant text passages. If the technology of retrieving texts where the answer might be found is well developed, few studies have been devoted to the recognition of the answer type.This paper presents a unified model of answer types for open-domain Question/Answering that enables the discovery of exact answers. The evaluation of the model, performed on real-world questions, considers both the correctness and the coverage of the answer types as well as their contribution to answer precision.