Retrieving descriptive phrases from large amounts of free text
Proceedings of the ninth international conference on Information and knowledge management
Large scale testing of a descriptive phrase finder
HLT '01 Proceedings of the first international conference on Human language technology research
Evaluating answers to definition questions
NAACL-Short '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: companion volume of the Proceedings of HLT-NAACL 2003--short papers - Volume 2
Learning to identify single-snippet answers to definition questions
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Multi-document summarization by sentence extraction
NAACL-ANLP-AutoSum '00 Proceedings of the 2000 NAACL-ANLP Workshop on Automatic Summarization
A text mining approach for definition question answering
FinTAL'06 Proceedings of the 5th international conference on Advances in Natural Language Processing
Overview of the CLEF 2005 multilingual question answering track
CLEF'05 Proceedings of the 6th international conference on Cross-Language Evalution Forum: accessing Multilingual Information Repositories
Overview of the CLEF 2006 multilingual question answering track
CLEF'06 Proceedings of the 7th international conference on Cross-Language Evaluation Forum: evaluation of multilingual and multi-modal information retrieval
Mining web snippets to answer list questions
AIDM '07 Proceedings of the 2nd international workshop on Integrating artificial intelligence and data mining - Volume 84
Hi-index | 0.00 |
This work presents Mdef-WQA, a system that searches for answers to definition questions in several languages on web snippets. For this purpose, Mdef-WQAbiases the search engine in favour of some syntactic structures that often convey definitions. Once descriptive sentences are identified, Mdef-WQAclusters them by potential sensesand presents the most relevant phrases of each potential senseto the user. The approach was assessed with TREC and CLEF data. As a result, Mdef-WQAwas able to extract descriptive information for all definition questions in the TREC 2001 and 2003 data-sets.