End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories

Rui Mao, Chenghua Lin, Frank Guerin

Research output: Contribution to conferencePaper

1 Downloads (Pure)

Abstract

End-to-end training with Deep Neural Networks (DNN) is a currently popular method for metaphor identification. However, standard sequence tagging models do not explicitly take advantage of linguistic theories of metaphor identification. We experiment with two DNN models which are inspired by two human metaphor identification procedures. By testing on three public datasets, we find that our models achieve state-of-the-art performance in end-to-end metaphor identification.
Original languageEnglish
Pages3888-3898
Number of pages11
DOIs
Publication statusPublished - Jul 2019
Event57th Annual Meeting of the Association for Computational Linguistics (ACL) - Fortezza da Basso, Florence, Italy
Duration: 28 Jul 20192 Aug 2019

Conference

Conference57th Annual Meeting of the Association for Computational Linguistics (ACL)
CountryItaly
CityFlorence
Period28/07/192/08/19

Fingerprint

Linguistics
Identification (control systems)
Testing
Experiments
Deep neural networks

Cite this

Mao, R., Lin, C., & Guerin, F. (2019). End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories. 3888-3898. Paper presented at 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy. https://doi.org/10.18653/v1/P19-1378

End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories. / Mao, Rui; Lin, Chenghua; Guerin, Frank.

2019. 3888-3898 Paper presented at 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy.

Research output: Contribution to conferencePaper

Mao, R, Lin, C & Guerin, F 2019, 'End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories', Paper presented at 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy, 28/07/19 - 2/08/19 pp. 3888-3898. https://doi.org/10.18653/v1/P19-1378
Mao R, Lin C, Guerin F. End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories. 2019. Paper presented at 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy. https://doi.org/10.18653/v1/P19-1378
Mao, Rui ; Lin, Chenghua ; Guerin, Frank. / End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories. Paper presented at 57th Annual Meeting of the Association for Computational Linguistics (ACL), Florence, Italy.11 p.
@conference{1819edc22bde4ade8589a2a11d957044,
title = "End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories",
abstract = "End-to-end training with Deep Neural Networks (DNN) is a currently popular method for metaphor identification. However, standard sequence tagging models do not explicitly take advantage of linguistic theories of metaphor identification. We experiment with two DNN models which are inspired by two human metaphor identification procedures. By testing on three public datasets, we find that our models achieve state-of-the-art performance in end-to-end metaphor identification.",
author = "Rui Mao and Chenghua Lin and Frank Guerin",
year = "2019",
month = "7",
doi = "10.18653/v1/P19-1378",
language = "English",
pages = "3888--3898",
note = "57th Annual Meeting of the Association for Computational Linguistics (ACL) ; Conference date: 28-07-2019 Through 02-08-2019",

}

TY - CONF

T1 - End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories

AU - Mao, Rui

AU - Lin, Chenghua

AU - Guerin, Frank

PY - 2019/7

Y1 - 2019/7

N2 - End-to-end training with Deep Neural Networks (DNN) is a currently popular method for metaphor identification. However, standard sequence tagging models do not explicitly take advantage of linguistic theories of metaphor identification. We experiment with two DNN models which are inspired by two human metaphor identification procedures. By testing on three public datasets, we find that our models achieve state-of-the-art performance in end-to-end metaphor identification.

AB - End-to-end training with Deep Neural Networks (DNN) is a currently popular method for metaphor identification. However, standard sequence tagging models do not explicitly take advantage of linguistic theories of metaphor identification. We experiment with two DNN models which are inspired by two human metaphor identification procedures. By testing on three public datasets, we find that our models achieve state-of-the-art performance in end-to-end metaphor identification.

U2 - 10.18653/v1/P19-1378

DO - 10.18653/v1/P19-1378

M3 - Paper

SP - 3888

EP - 3898

ER -