What Syntax Can Contribute in the Entailment Task

  • Lucy Vanderwende
  • William B. Dolan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3944)


We describe our submission to the PASCAL Recognizing Textual Entailment Challenge, which attempts to isolate the set of Text-Hypothesis pairs whose categorization can be accurately predicted based solely on syntactic cues. Two human annotators examined each pair, showing that a surprisingly large proportion of the data – 34% of the test items – can be handled with syntax alone, while adding information from a general-purpose thesaurus increases this to 48%.


Test Item Entity Recognition Prepositional Phrase Syntactic Analysis Human Annotator 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Collins, M., Duffy, N.: New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron. In: Proceedings of ACL 2002, Philadelphia, PA (2002)Google Scholar
  2. 2.
    Dagan, I., Glickman, O., Magnini, B.: The PASCAL Recognising Textual Entailment Challenge. In: The Proceedings of the PASCAL Recognising Textual Entailment Challenge (April 2005 )Google Scholar
  3. 3.
    Gildea, D., Jurafsky, D.: Automatic Labeling of Semantic Roles. Computational Linguistics 28(3), 245–288 (2002)CrossRefGoogle Scholar
  4. 4.
    Hacioglu, K., Pradhan, S., Ward, W., Martin, J.H., Jurafsky, D.: Semantic Role Labeling by Tagging Syntactic Chunks. In: Proceedings of the Eighth Conference on Natural Language Learning (CONLL 2004), Boston,MA, May 6-7 (2004)Google Scholar
  5. 5.
    Henderson, J.: Discriminative training of a neural network statistical parser. In: Proceedings of ACL 2004, Barcelona, Spain (2004)Google Scholar
  6. 6.
    Ringger, E., Moore, R.C., Charniak, E., Vanderwende, L., Suzuki, H.: Using the Penn Treebank to Evaluate Non-Treebank Parsers. In: Proceedings of the 2004 Language Resources and Evaluation Conference (LREC), Lisbon, Portugal (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Lucy Vanderwende
    • 1
  • William B. Dolan
    • 1
  1. 1.Microsoft ResearchRedmondUSA

Personalised recommendations