Effectively Using Syntax for Recognizing False Entailment

Abstract

Recognizing textual entailment is a challenging problem and a fundamental component of many applications in natural language processing. We present a novel framework for recognizing textual entailment that focuses on the use of syntactic heuristics to recognize false entailment. We give a thorough analysis of our system, which demonstrates state-of-the-art performance on a widely-used test set.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2006
Accession Number
ADA456695

Entities

People

  • Arul Menezes
  • Lucy Vanderwende
  • Rion Snow

Organizations

  • Stanford University

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Acquisition
  • Black Holes
  • Computational Linguistics
  • Computer Science
  • Data Sets
  • Language
  • Linguistics
  • Machine Translation
  • Natural Language Processing
  • Natural Languages
  • New York
  • Reasoning
  • Recognition
  • Template Patterns
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Computational Linguistics

Technology Areas

  • AI & ML
  • AI & ML - Information Retrieval
  • AI & ML - Machine Learning Algorithms