Sensorimotor Enhanced Neural Network for Metaphor Detection

Mingyu Wan; Baixi Xing; Qi Su; Pengyuan Liu; Chu-Ren Huang

Sensorimotor Enhanced Neural Network for Metaphor Detection

Mingyu Wan
, Baixi Xing
, Qi Su
, Pengyuan Liu
, Chu-Ren Huang

Department of Language Science and Technology

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

5 Citations (Scopus)

Abstract

Detecting metaphors is challenging due to the subtle ontological differences between metaphorical and non-metaphorical expressions. Neural networks have been widely adopted in metaphor detection and become the main stream technology. However, linguistic insights have been less utilized. This work
proposes a linguistically enhanced model for metaphor detection extending one published work (WAN et al., 2020) by incorporating the modality norms into attention-based Bi-LSTM. Results show that the current model outperforms most recent works by 0.5%-11% F1, indicating the effectiveness of using modality norms for metaphor detection. This work provides a new perspective to detect token-level metaphoricity by leveraging the modality mismatch between words.

Original language	English
Title of host publication	Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation
Editors	Minh Le Nguyen, Mai Chi Luong, Sanghoun Song
Publisher	Association for Computational Linguistics (ACL)
Pages	312-317
Publication status	Published - Oct 2020
Event	The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC-34) - Vietnam National University, Hanoi, Viet Nam Duration: 24 Oct 2020 → 26 Oct 2020

Conference

Conference	The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC-34)
Country/Territory	Viet Nam
City	Hanoi
Period	24/10/20 → 26/10/20

ASJC Scopus subject areas

Language and Linguistics
Computer Science (miscellaneous)

More information

https://aclanthology.org/2020.paclic-1.36

Cite this

@inproceedings{e7d3006149ed470aad3d6bf9679bd001,

title = "Sensorimotor Enhanced Neural Network for Metaphor Detection",

abstract = "Detecting metaphors is challenging due to the subtle ontological differences between metaphorical and non-metaphorical expressions. Neural networks have been widely adopted in metaphor detection and become the main stream technology. However, linguistic insights have been less utilized. This work proposes a linguistically enhanced model for metaphor detection extending one published work (WAN et al., 2020) by incorporating the modality norms into attention-based Bi-LSTM. Results show that the current model outperforms most recent works by 0.5\%-11\% F1, indicating the effectiveness of using modality norms for metaphor detection. This work provides a new perspective to detect token-level metaphoricity by leveraging the modality mismatch between words.",

author = "Mingyu Wan and Baixi Xing and Qi Su and Pengyuan Liu and Chu-Ren Huang",

note = "Publisher Copyright: {\textcopyright} PACLIC 2020.All rights reserved.; The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC-34) ; Conference date: 24-10-2020 Through 26-10-2020",

year = "2020",

month = oct,

language = "English",

pages = "312--317",

editor = "Nguyen, \{Minh Le\} and Luong, \{Mai Chi\} and Sanghoun Song",

booktitle = "Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation",

publisher = "Association for Computational Linguistics (ACL)",

}

Wan, M, Xing, B, Su, Q, Liu, P & Huang, C-R 2020, Sensorimotor Enhanced Neural Network for Metaphor Detection. in ML Nguyen, MC Luong & S Song (eds), Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation. Association for Computational Linguistics (ACL), pp. 312-317, The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC-34), Hanoi, Viet Nam, 24/10/20. <https://aclanthology.org/2020.paclic-1.36>

Sensorimotor Enhanced Neural Network for Metaphor Detection. / Wan, Mingyu; Xing, Baixi; Su, Qi et al.
Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation. ed. / Minh Le Nguyen; Mai Chi Luong; Sanghoun Song. Association for Computational Linguistics (ACL), 2020. p. 312-317.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Sensorimotor Enhanced Neural Network for Metaphor Detection

AU - Wan, Mingyu

AU - Xing, Baixi

AU - Su, Qi

AU - Liu, Pengyuan

AU - Huang, Chu-Ren

PY - 2020/10

Y1 - 2020/10

N2 - Detecting metaphors is challenging due to the subtle ontological differences between metaphorical and non-metaphorical expressions. Neural networks have been widely adopted in metaphor detection and become the main stream technology. However, linguistic insights have been less utilized. This work proposes a linguistically enhanced model for metaphor detection extending one published work (WAN et al., 2020) by incorporating the modality norms into attention-based Bi-LSTM. Results show that the current model outperforms most recent works by 0.5%-11% F1, indicating the effectiveness of using modality norms for metaphor detection. This work provides a new perspective to detect token-level metaphoricity by leveraging the modality mismatch between words.

AB - Detecting metaphors is challenging due to the subtle ontological differences between metaphorical and non-metaphorical expressions. Neural networks have been widely adopted in metaphor detection and become the main stream technology. However, linguistic insights have been less utilized. This work proposes a linguistically enhanced model for metaphor detection extending one published work (WAN et al., 2020) by incorporating the modality norms into attention-based Bi-LSTM. Results show that the current model outperforms most recent works by 0.5%-11% F1, indicating the effectiveness of using modality norms for metaphor detection. This work provides a new perspective to detect token-level metaphoricity by leveraging the modality mismatch between words.

UR - https://www.scopus.com/pages/publications/105037859489

M3 - Conference article published in proceeding or book

SP - 312

EP - 317

BT - Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation

A2 - Nguyen, Minh Le

A2 - Luong, Mai Chi

A2 - Song, Sanghoun

PB - Association for Computational Linguistics (ACL)

T2 - The 34th Pacific Asia Conference on Language, Information and Computation (PACLIC-34)

Y2 - 24 October 2020 through 26 October 2020

ER -

Sensorimotor Enhanced Neural Network for Metaphor Detection

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this