Paraphrase Substitution for Recognizing Textual Entailment

We describe a method for recognizing textual entailment that uses the length of the longest common subsequence (LCS) between two texts as its decision criterion. Rather than requiring strict word matching in the common subsequences, we perform a flexible match using automatically generated paraphrases.We find that the use of paraphrases over strict word matches represents an average F-measure improvement from 0.22 to 0.36 on the CLEF 2006 Answer Validation Exercise for 7 languages.

[1]  Xavier Carreras,et al.  FreeLing: An Open-Source Suite of Language Analyzers , 2004, LREC.

[2]  Philipp Koehn,et al.  Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[3]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[4]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[5]  Gertjan van Noord,et al.  Alpino: Wide-coverage Computational Analysis of Dutch , 2000, CLIN.

[6]  Lucy Vanderwende,et al.  What Syntax Can Contribute in the Entailment Task , 2005, MLCW.

[7]  Regina Barzilay,et al.  Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment , 2003, NAACL.

[8]  Chris Callison-Burch,et al.  Paraphrasing with Bilingual Parallel Corpora , 2005, ACL.

[9]  Roy Bar-Haim,et al.  The Second PASCAL Recognising Textual Entailment Challenge , 2006 .

[10]  Vladimir Naumovich Vapni The Nature of Statistical Learning Theory , 1995 .

[11]  Ido Dagan,et al.  The Third PASCAL Recognizing Textual Entailment Challenge , 2007, ACL-PASCAL@ACL.

[12]  Regina Barzilay,et al.  Extracting Paraphrases from a Parallel Corpus , 2001, ACL.

[13]  Philipp Koehn,et al.  A parallel corpus for statistical machine translation , 2005 .

[14]  M. Felisa Verdejo,et al.  Overview of the Answer Validation Exercise 2007 , 2007, CLEF.

[15]  Daniel Marcu,et al.  Syntax-based Alignment of Multiple Translations: Extracting Paraphrases and Generating New Sentences , 2003, NAACL.

[16]  Cordelia Schmid,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[17]  Emiel Krahmer,et al.  Normalized alignment of dependency trees for detecting textual entailment , 2006 .

[18]  Dekang Lin,et al.  Dependency-Based Evaluation of Minipar , 2003 .

[19]  M. Felisa Verdejo,et al.  Overview of the Answer Validation Exercise 2006 , 2006, CLEF.