Recognizing Textual Entailment by Soft Dependency Tree Matching

Authors

  • Rohini Basak Jadavpur University
  • Sudip Kumar Naskar Jadavpur University
  • Partha Pakray National Institute of Technology
  • Alexander Gelbukh Instituto Politécnico Nacional

DOI:

https://doi.org/10.13053/cys-19-4-2331

Keywords:

textual entailment, dependency parsing, dependency relation matching, rules, PETE dataset

Abstract

We present a rule-based method for recognizing entailment relation between a pair of text fragments by comparing their dependency tree structures. We used a dependency parser to generate the dependency triples of the text–hypothesis pairs. A dependency triple is an arc in the dependency parse tree. Each triple in the hypothesis is checked against all the triples in the text to find a matching pair. We have developed a number of matching rules after a detailed analysis of the PETE dataset, which we used for the experiments. A successful match satisfying any of these rules assigns a matching score of 1 to the child node of that particular arc in the hypothesis dependency tree. Then the dependency parse tree is traversed in post-order way to obtain the final entailment score at the root node. The scores of the leaf nodes are propagated from the bottom of the tree to the non-leaf nodes, up to the root node. The entailment score of the root node is compared against a predefined threshold value to make the entailment decision. Experimental results on the PETE dataset show an accuracy of 87.69% on the development set and 73.75% on the test set, which outperforms the state-of-the-art results reported on this dataset so far. We did not use any other NLP tools or knowledge sources, to emphasize the role of dependency parsing in recognizing textual entailment.

Author Biographies

Rohini Basak, Jadavpur University

is pursuing her Ph.D. degree from the Jadavpur University, at the department of Computer Science and Engineering. She is also a guest faculty at the same university since February 2015. She formerly worked as an Assistant Systems Engineer for TATA Consultancy Services Ltd. in 2010. Her areas of teaching include data structures, object-oriented programming, numerical methods, C program­ming, computer organization, and computer networks. Her research work is mainly focused on recognizing textual entailment.

Sudip Kumar Naskar, Jadavpur University

obtained his PhD in Computer Science and Engineering from Jadavpur University, India. He is currently Assistant Professor at the Computer Science and Engineering Department of the Jadavpur University. Before, he was a postdoctoral researcher at the Centre for Next Generation Localisation (CNGL), at the MT Research Group of the National Centre for Language Technology, School of Computing of the Dublin City University, Ireland. His research interests are focused on machine translation and word sense disambiguation. He is an author of more than 70 research publications.

Partha Pakray, National Institute of Technology

received a Ph.D. degree in Computer Science and Engineering from the Jadavpur University, India. He is currently Head and Assistant Professor at the Department of Computer Science and Engineering of the National Institute of Technology Mizoram. He received fellowship from European Research Consortium for Informatics and Mathematics (ERCIM) for two times and worked at the Norwegian University of Science and Technology, Norway, and the Masaryk University, Czech Republic, as a postdoctoral fellow. He also worked at the Xerox Research Centre Europe (XRCE) as a research intern. He has published 45 research publications in various areas of natural language processing.

Alexander Gelbukh, Instituto Politécnico Nacional

received an MSc degree in Mathematics from the Lomonosov Moscow State University, Russia, and a Ph.D. in Computer Science from VINITI, Russia. He is currently a Research Professor and Head of the Natural Language Processing Laboratory of the Center for Computing Research (Centro de Investigación in Computación, CIC) of the Instituto Politécnico Nacional (IPN), Mexico. He is a former President of the Mexican Society of Artificial Intelligence (SMIA), a Member of the Mexican Academy of Sciences, and a National Researcher of Mexico (SNI) at excellence level 2. He is author or coauthor of more than 500 research publications in natural language processing and artificial intelligence.

Downloads

Published

2015-12-18

Issue

Vol. 19 No. 4 (2015): 19(4) 2015 Thematic issue: Computational Linguistics (Guest editor: A. Gelbukh)

Section

Articles

License 

Hereby I transfer exclusively to the Journal "Computación y 
Sistemas", published by the Computing Research Center (CIC-IPN),
the Copyright of the aforementioned paper. I also accept that these 
rights will not be transferred to any other publication, in any other 
format, language or other existing means of developing.
I certify that the paper has not been previously disclosed or simultaneo
usly submitted to any other publication, and that it does not contain 
material whose publication would violate the Copyright or other 
proprietary rights of any person, company or institution. I certify that 
I have the permission from the institution or company where I work or 
study to publish this work.
The representative author accepts the responsibility for the publication
of this paper on behalf of each and every one of the authors. 
This transfer is subject to the following conditions:
  • The authors retain all ownership rights (such as patent rights) of this work, except for the publishing rights transferred to the CIC, through this document.
  • Authors retain the right to publish the work in whole or in part in any book they are the authors or publishers. They can also make use of this work in conferences, courses, personal web pages, and so on.
  • Authors may include working as part of his thesis, for non-profit distribution only.