|Abstract||This paper proposes a new architecture for textual inference in which ﬁnding a good alignment is separated from evaluating entailment. Current approaches to semantic inference in question answering and textual entailment have approximated the entailment problem as that of computing the best alignment of the hypothesis to the text, using a locally decomposable matching score. While this formulation is adequate for representing local (word-level) phenomena such as synonymy, it is incapable of representing global interactions, such as that between verb negation and the addition/removal of qualiﬁers, which are often critical for determining entailment. We propose a pipelined approach where alignment is followed by a classiﬁcation step, in which we extract features representing high-level characteristics of the entailment problem, and give the resulting feature vector to a statistical classiﬁer trained on development data.|
|Keywords||No keywords specified (fix it)|
|Categories||No categories specified (fix it)|
|Through your library||Only published papers are available at libraries|
Similar books and articles
David Hall, Christopher D. Manning, Daniel Cer & Chloe Kiddon, Learning Alignments and Leveraging Natural Logic.
Christopher Cox, Christopher D. Manning & Kristina Toutanova, Robust Textual Inference Using Diverse Knowledge Sources.
Janusz Czelakowski (1983). Some Theorems on Structural Entailment Relations. Studia Logica 42 (4):417 - 429.
Neil Tennant (1984). Perfect Validity, Entailment and Paraconsistency. Studia Logica 43 (1-2):181 - 200.
G. Politzer (2007). The Psychological Reality of Classical Quantifier Entailment Properties. Journal of Semantics 24 (4):331-343.
B. A. Davey, M. Haviar & H. A. Priestley (1995). The Syntax and Semantics of Entailment in Duality Theory. Journal of Symbolic Logic 60 (4):1087-1114.
Added to index2010-12-22
Total downloads3 ( #202,008 of 549,094 )
Recent downloads (6 months)2 ( #37,390 of 549,094 )
How can I increase my downloads?