Relation Alignment for Textual Entailment Recognition

Mark Sammons     VG Vinod Vydiswaran     Tim Vieira     Nikhil Johri     Ming-Wei Chang     Dan Goldwasser     Vivek Srikumar     Gourab Kundu     Yuancheng Tu     Kevin Small     Joshua Rule     Quang Do     Dan Roth    
Text Analysis Conference (TAC), 2009
[pdf]

Abstract

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


Bib Entry

  @InProceedings{SVVJCGSKTSRDR_tac_2009,
    author = "Mark Sammons and VG Vinod Vydiswaran and Tim Vieira and Nikhil Johri and Ming-Wei Chang and Dan Goldwasser and Vivek Srikumar and Gourab Kundu and Yuancheng Tu and Kevin Small and Joshua Rule and Quang Do and Dan Roth",
    title = "Relation Alignment for Textual Entailment Recognition",
    booktitle = "Text Analysis Conference (TAC)",
    year = "2009"
  }