An inference model for semantic entailment in natural language

作者: Rodrigo de Salvo Braz , Roxana Girju , Vasin Punyakanok , Dan Roth , Mark Sammons

DOI: 10.1007/11736790_15

关键词:

摘要: Semantic entailment is the problem of determining if meaning a given sentence entails that another. This fundamental in natural language understanding provides broad framework for studying variability and has large number applications. paper presents principled approach to this builds on inducing representations text snippets into hierarchical knowledge representation along with sound optimization-based inferential mechanism makes use it decide semantic entailment. A preliminary evaluation PASCAL collection presented.

参考文章(25)
J. W. Lloyd, Foundations of logic programming; (2nd extended ed.) Springer-Verlag New York, Inc.. ,(1987)
Andrew Y. Ng, Rajat Raina, Christopher D. Manning, Robust textual inference via learning and abductive reasoning national conference on artificial intelligence. pp. 1099- 1105 ,(2005)
Ido Dagan, Oren Glickman, Moshe Koppel, A probabilistic classification approach for lexical textual entailment national conference on artificial intelligence. pp. 1050- 1055 ,(2005)
Lenhart K. Schubert, Francis Jeffry Pelletier, From English to logic: context-free computation of conventional logical translation Computational Linguistics. ,vol. 8, pp. 26- 44 ,(1982) , 10.7939/R3VQ2SR1G
Vasin Punyakanok, Wen-tau Yih, Dan Roth, The necessity of syntactic parsing for semantic role labeling international joint conference on artificial intelligence. pp. 1117- 1123 ,(2005)
Peter F. Patel-Schneider, Deborah L. McGuinness, Diego Calvanese, Franz Baader, Daniele Nardi, The Description Logic Handbook ,(2009)
Paul Morie, Dan Roth, Xin Li, Identification and tracing of ambiguous names: discriminative and generative approaches national conference on artificial intelligence. pp. 419- 424 ,(2004)
Wen-tau Yih, Dan Roth, A Linear Programming Formulation for Global Inference in Natural Language Tasks conference on computational natural language learning. pp. 1- 8 ,(2004)