Welcome to the InfoSci Platform
Reference Hub1
A Lexico-Syntactic-Semantic Approach to Recognizing Textual Entailment

A Lexico-Syntactic-Semantic Approach to Recognizing Textual Entailment

Rohini Basak, Sudip Kumar Naskar, Alexander Gelbukh
Copyright: © 2020 |Pages: 41
ISBN13: 9781799830382|ISBN10: 1799830381|ISBN13 Softcover: 9781799830399|EISBN13: 9781799830405
DOI: 10.4018/978-1-7998-3038-2.ch010
Cite Chapter Cite Chapter

MLA

Basak, Rohini, et al. "A Lexico-Syntactic-Semantic Approach to Recognizing Textual Entailment." Innovations, Algorithms, and Applications in Cognitive Informatics and Natural Intelligence, edited by Kwok Tai Chui, et al., IGI Global, 2020, pp. 187-227. https://doi.org/10.4018/978-1-7998-3038-2.ch010

APA

Basak, R., Naskar, S. K., & Gelbukh, A. (2020). A Lexico-Syntactic-Semantic Approach to Recognizing Textual Entailment. In K. Chui, M. Lytras, R. Liu, & M. Zhao (Eds.), Innovations, Algorithms, and Applications in Cognitive Informatics and Natural Intelligence (pp. 187-227). IGI Global. https://doi.org/10.4018/978-1-7998-3038-2.ch010

Chicago

Basak, Rohini, Sudip Kumar Naskar, and Alexander Gelbukh. "A Lexico-Syntactic-Semantic Approach to Recognizing Textual Entailment." In Innovations, Algorithms, and Applications in Cognitive Informatics and Natural Intelligence, edited by Kwok Tai Chui, et al., 187-227. Hershey, PA: IGI Global, 2020. https://doi.org/10.4018/978-1-7998-3038-2.ch010

Export Reference

Mendeley
Favorite

Abstract

Given two textual fragments, called a text and a hypothesis, respectively, recognizing textual entailment (RTE) is a task of automatically deciding whether the meaning of the second fragment (hypothesis) logically follows from the meaning of the first fragment (text). The chapter presents a method for RTE based on lexical similarity, dependency relations, and semantic similarity. In this method, called LSS-RTE, each of the two fragments is converted to a dependency graph, and the two obtained graph structures are compared using dependency triple matching rules, which have been compiled after a thorough and detailed analysis of various RTE development datasets. Experimental results show 60.5%, 64.4%, 62.8%, and 61.5% accuracy on the well-known RTE1, RTE2, RTE3, and RTE4 datasets, respectively, for the two-way classification task and 54.3% accuracy for three-way classification task on the RTE4 dataset.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.