A simple hybrid approach to recognizing textual entailment

Issue title: Intelligent and Fuzzy Systems applied to Language & Knowledge Engineering

Guest editors: David Pinto, Vivek Kumar Singh, Aline Villavicencio, Philipp Mayr-Schlegel and Efstathios Stamatatos

Article type: Research Article

Authors: Basak, Rohini^a | Naskar, Sudip Kumar^a | Gelbukh, Alexander^{b; *}

Affiliations: [a] Jadavpur University, Kolkata, India | [b] CIC, Instituto Politécnico Nacional, Mexico City, Mexico

Correspondence: [*] Corresponding author. Alexander Gelbukh, CIC, Instituto Politécnico Nacional, 07738 Mexico City, Mexico. gelbukh@gelbukh.com.

Abstract: We explore various machine learning-based classifiers applied to rule-based features for recognizing textual entailment. The features, extracted with a set of synthesized matching rules, reflect syntactic and semantic similarity between the text and the hypothesis. The fact that we use only seven relatively simple features makes our method suitable for low-resource languages. We test our method on the test sets of the RTE competitions and achieve accuracy of up to 69.13%.

Keywords: Textual entailment, dependency parsing, semantic similarity, supervised machine learning, RTE datasets

DOI: 10.3233/JIFS-169474

Journal: Journal of Intelligent & Fuzzy Systems, vol. 34, no. 5, pp. 2873-2885, 2018