A multilingual framework for searching definitions on web snippets

Alejandro Figueroa; Günter Neumann

In: J. Hertzberg; M. Beetz; R. Englert (Hrsg.). Proceedings of the 30th Annual German Conference on Artificial Intelligence. German Conference on Artificial Intelligence (KI-2007), Osnabrück, Germany, Pages 144-159, LNCS, Vol. 4667, Springer, 2007.


This work presents Mdef-WQA, a system that searches for answers to definition questions in several languages on web snippets. For this purpose, Mdef-WQA biases the search engine in favour of some syntactic structures that often convey definitions. Once descriptive sentences are identified, Mdef-WQA clusters them by potential senses and presents the most relevant phrases of each potential sense to the user. The approach was assessed with TREC and CLEF data. As a result, Mdef-WQA was able to extract descriptive information for all definition questions in the TREC 2001 and 2003 data-sets.

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence