Siamese Convolutional Neural Networks for Recognizing Partial
Entailment

D 2018

Siamese Convolutional Neural Networks for Recognizing Partial Entailment

VÍTA, Martin

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

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

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

Změněno: 29/3/2021 17:00, RNDr. Pavel Šmerk, Ph.D.

Abstract

V originále

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

Citovat

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.

@inproceedings{1458718,
   author = {Víta, Martin},
   address = {Brno},
   booktitle = {Siamese Convolutional Neural Networks for Recognizing Partial Entailment},
   editor = {J. Zendulka, M. Bieliková, R. Burget, Z. Křivka (eds.)},
   keywords = {Partial Textual Entailment; Convolutional Neural Networks; Siamese Architectures},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Brno},
   isbn = {978-80-214-5679-2},
   pages = {237-242},
   publisher = {Vysoké učení technické v Brně},
   title = {Siamese Convolutional Neural Networks for Recognizing Partial Entailment},
   url = {http://daz2018.fit.vutbr.cz/DaZ_WIKT_2018_Sbornik.pdf},
   year = {2018}
}

TY  - JOUR
ID  - 1458718
AU  - Víta, Martin
PY  - 2018
TI  - Siamese Convolutional Neural Networks for Recognizing Partial Entailment
PB  - Vysoké učení technické v Brně
CY  - Brno
SN  - 9788021456792
KW  - Partial Textual Entailment
KW  - Convolutional Neural Networks
KW  - Siamese Architectures
UR  - http://daz2018.fit.vutbr.cz/DaZ_WIKT_2018_Sbornik.pdf
L2  - http://daz2018.fit.vutbr.cz/DaZ_WIKT_2018_Sbornik.pdf
N2  - 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.
ER  -

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

Detailed Information on Publication Record