Siamese Convolutional Neural Networks for Recognizing Partial Entailment

VÍTA, Martin. Siamese Convolutional Neural Networks for Recognizing Partial Entailment. Online. In J. Zendulka, M. Bieliková, R. Burget, Z. Křivka (eds.). Siamese Convolutional Neural Networks for Recognizing Partial Entailment. Brno: Vysoké učení technické v Brně, 2018, p. 237-242. ISBN 978-80-214-5679-2.

Basic information

• Original name: Siamese Convolutional Neural Networks for Recognizing Partial Entailment
• Authors: VÍTA, Martin (203 Czech Republic, guarantor, belonging to the institution).
• Edition: Brno, Siamese Convolutional Neural Networks for Recognizing Partial Entailment, p. 237-242, 6 pp. 2018.
• Publisher: Vysoké učení technické v Brně

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Czech Republic
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: electronic version available online
• WWW: Full paper
• RIV identification code: RIV/00216224:14330/18:00115010
• Organization unit: Faculty of Informatics
• ISBN: 978-80-214-5679-2
• Keywords in English: Partial Textual Entailment; Convolutional Neural Networks; Siamese Architectures

Abstract

Recognizing textual entailment (RTE), i. e., a decision problem whether a sentence (called hypothesis) can be inferred from a given text, became a well established and widely studied task. As a consequence of the traditional binary (or ternary) class formulation, it is not possible to express the fact that a fragment of the hypothesis is entailed by the text, even though the “whole” entailment of the hypothesis from the text does not hold. The notions of partial textual entailment – and faceted entailment in particular – address this problem. In this paper, we introduce a siamese CNN architecture with a static attention mechanism together with a sentence compression and provide an evaluation over modified SemEval 2013 Task 8 dataset.

Links

• MUNI/A/0854/2017, interní kód MU: Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VII.

Investor: Masaryk University, Category A