Relation Alignment for Textual Entailment Recognition

We present an approach to textual entailment recognition, in which inference is based on a shallow semantic representation of relations (predicates and their arguments) in the text and hypothesis of the entailment pair, and in which specialized knowledge is encapsulated in modular components with very simple interfaces. We propose an architecture designed to integrate different, unscaled Natural Language Processing resources, and demonstrate an alignment-based method for combining them. We clarify the purpose of alignment in the RTE task, identifying two distinct alignment models, each of which leads to a different type of entailment system. We identify desirable properties of alignment, and use this to inform our implementation of an alignment component. We evaluate the resulting system on the RTE5 data set, and use an ablation study to assess the conformance of our alignment approach with these desired characteristics.

[1]  Dan Roth,et al.  Understanding the Value of Features for Coreference Resolution , 2008, EMNLP.

[2]  Dan Roth,et al.  A Unified Representation and Inference Paradigm for Natural Language , 2008 .

[3]  Martha Palmer,et al.  Adding predicate argument structure to the Penn TreeBank , 2002 .

[4]  Christopher D. Manning,et al.  A Phrase-Based Alignment Model for Natural Language Inference , 2008, EMNLP.

[5]  Christopher D. Manning,et al.  Aligning Semantic Graphs for Textual Inference and Machine Reading , 2007 .

[6]  Christopher D. Manning,et al.  Learning to recognize features of valid textual entailments , 2006, NAACL.

[7]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[8]  Patrick Pantel,et al.  DIRT @SBT@discovery of inference rules from text , 2001, KDD '01.

[9]  Dan Roth,et al.  The Importance of Syntactic Parsing and Inference in Semantic Role Labeling , 2008, CL.

[10]  Ido Dagan,et al.  Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition , 2007, ACL-PASCAL@ACL.

[11]  Dekang Lin,et al.  DIRT – Discovery of Inference Rules from Text , 2001 .

[12]  Andrew Hickl,et al.  Recognizing Textual Entailment with LCC’s G ROUNDHOG System , 2005 .

[13]  Martha Palmer,et al.  Class-Based Construction of a Verb Lexicon , 2000, AAAI/IAAI.

[14]  George A. Miller,et al.  Introduction to WordNet: An On-line Lexical Database , 1990 .

[15]  Ido Dagan,et al.  Semantic Inference at the Lexical-Syntactic Level , 2007, AAAI.

[16]  Mitchell P. Marcus,et al.  Adding Semantic Annotation to the Penn TreeBank , 1998 .

[17]  Dan Roth,et al.  Part of Speech Tagging Using a Network of Linear Separators , 1998, ACL.

[18]  D. Roth,et al.  Inference with Classifiers : The Phrase Identification Problem Inference with Classifiers : The Phrase Identification Problem ∗ , 2004 .

[19]  Dan Roth,et al.  Design Challenges and Misconceptions in Named Entity Recognition , 2009, CoNLL.

[20]  Alessandro Moschitti,et al.  Automatic Learning of Textual Entailments with Cross-Pair Similarities , 2006, ACL.

[21]  Sanda M. Harabagiu,et al.  Textual Entailment Through Extended Lexical Overlap and Lexico-Semantic Matching , 2007, ACL-PASCAL@ACL.

[22]  Eugene Charniak,et al.  Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking , 2005, ACL.

[23]  Ming-Wei Chang,et al.  Discriminative Learning over Constrained Latent Representations , 2010, NAACL.

[24]  K. Markert,et al.  When logical inference helps determining textual entailment ( and when it doesn ’ t ) , .

[25]  Chris Brockett,et al.  Aligning the RTE 2006 Corpus , 2007 .