Summary of the paper
| Title | Mining Wikipedia for Large-scale Repositories of Context-Sensitive Entailment Rules |
|---|---|
| Authors | Milen Kouylekov, Yashar Mehdad and Matteo Negri |
| Abstract | This paper focuses on the central role played by lexical information in thetask of Recognizing Textual Entailment. In particular, the usefulness oflexical knowledge extracted from several widely used static resources,represented in the form of entailment rules, is compared with a method toextract lexical information from Wikipedia as a dynamic knowledge resource. Theproposed acquisition method aims at maximizing two key features of theresulting entailment rules: coverage (i.e. the proportion of rules successfullyappliedover a dataset of TE pairs), and context sensitivity (i.e. the proportion ofrules applied in appropriate contexts). Evaluation results show that Wikipediacan be effectively used as a source of lexical entailment rules, featuring bothhigher coverage and context sensitivity with respect to other resources. |
| Language | Knowledge Discovery/Representation |
| Topics | Textual Entailment and Paraphrasing, Tools, systems, applications, Knowledge Discovery/Representation |
Full paper  |
Mining Wikipedia for Large-scale Repositories of Context-Sensitive Entailment Rules |
| Bibtex | @InProceedings{KOUYLEKOV10.425, author = {Milen Kouylekov, Yashar Mehdad and Matteo Negri}, title = {Mining Wikipedia for Large-scale Repositories of Context-Sensitive Entailment Rules}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |