A syntactic textual entailment system based on dependency parser

Authors:
Partha Pakray;Alexander Gelbukh;Sivaji Bandyopadhyay
Affiliations:
Computer Science and Engineering Department, Jadavpur University, Kolkata, India;Center for Computing Research, National Polytechnic Institute, Mexico City, Mexico;Computer Science and Engineering Department, Jadavpur University, Kolkata, India
Venue:
CICLing'10 Proceedings of the 11th international conference on Computational Linguistics and Intelligent Text Processing
Year:
2010

Citing 6
Cited 1

Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Recognizing textual entailment using sentence similarity based on dependency tree skeletons

RTE '07 Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing
The role of sentence structure in recognizing textual entailment

RTE '07 Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing
The PASCAL recognising textual entailment challenge

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment
What syntax can contribute in the entailment task

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment
Textual entailment recognition based on dependency analysis and wordnet

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment

Answer validation through textual entailment

NLDB'11 Proceedings of the 16th international conference on Natural language processing and information systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The development of a syntactic textual entailment system that compares the dependency relations in both the text and the hypothesis has been reported. The Stanford Dependency Parser has been run on the 2-way RTE-3 development set and the dependency relations obtained for a text and hypothesis pair has been compared. Some of the important comparisons are: subject-subject comparison, subject-verb comparison, object-verb comparison and cross subject-verb comparison. Corresponding verbs are further compared using the WordNet. Each of the matches is assigned some weight learnt from the development corpus. A threshold has been set on the fraction of matching hypothesis relations based on the development set. The threshold score has been applied on the RTE-4 gold standard test set using the same methods of dependency parsing followed by comparisons. Evaluation scores obtained on the test set show 54.75% precision and 53% recall for YES decisions and 54.45% precision and 56.2% recall for NO decisions.