Word Embedding and WordNet Based Metaphor Identification and Interpretation

Rui Mao, Chenghua Lin, Frank Guerin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)
12 Downloads (Pure)

Abstract

Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly.
Original languageEnglish
Title of host publicationProceedings of the 56th Annual Meeting of the Association for Computational Linguistics
Place of PublicationMelbourne, Australia
PublisherAssociation for Computational Linguistics (ACL)
Pages1222-1231
Number of pages10
Volume1: Long Papers
ISBN (Print)978-1-948087-32-2
Publication statusPublished - 17 Jul 2018
EventThe 56th Annual Meeting of the Association for Computational Linguistics - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018

Conference

ConferenceThe 56th Annual Meeting of the Association for Computational Linguistics
CountryAustralia
CityMelbourne
Period15/07/1820/07/18

Fingerprint

Identification (control systems)
Unsupervised learning
Processing

Keywords

  • Metaphor Identification
  • Metaphor Interpretation
  • Word Embedding output vector

Cite this

Mao, R., Lin, C., & Guerin, F. (2018). Word Embedding and WordNet Based Metaphor Identification and Interpretation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers, pp. 1222-1231). Melbourne, Australia: Association for Computational Linguistics (ACL).

Word Embedding and WordNet Based Metaphor Identification and Interpretation. / Mao, Rui; Lin, Chenghua; Guerin, Frank.

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics . Vol. 1: Long Papers Melbourne, Australia : Association for Computational Linguistics (ACL), 2018. p. 1222-1231.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mao, R, Lin, C & Guerin, F 2018, Word Embedding and WordNet Based Metaphor Identification and Interpretation. in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics . vol. 1: Long Papers, Association for Computational Linguistics (ACL), Melbourne, Australia, pp. 1222-1231, The 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15/07/18.
Mao R, Lin C, Guerin F. Word Embedding and WordNet Based Metaphor Identification and Interpretation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics . Vol. 1: Long Papers. Melbourne, Australia: Association for Computational Linguistics (ACL). 2018. p. 1222-1231
Mao, Rui ; Lin, Chenghua ; Guerin, Frank. / Word Embedding and WordNet Based Metaphor Identification and Interpretation. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics . Vol. 1: Long Papers Melbourne, Australia : Association for Computational Linguistics (ACL), 2018. pp. 1222-1231
@inproceedings{1073cf6a142a4027b255520b158ca93b,
title = "Word Embedding and WordNet Based Metaphor Identification and Interpretation",
abstract = "Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly.",
keywords = "Metaphor Identification, Metaphor Interpretation, Word Embedding output vector",
author = "Rui Mao and Chenghua Lin and Frank Guerin",
year = "2018",
month = "7",
day = "17",
language = "English",
isbn = "978-1-948087-32-2",
volume = "1: Long Papers",
pages = "1222--1231",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Word Embedding and WordNet Based Metaphor Identification and Interpretation

AU - Mao, Rui

AU - Lin, Chenghua

AU - Guerin, Frank

PY - 2018/7/17

Y1 - 2018/7/17

N2 - Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly.

AB - Metaphoric expressions are widespread in natural language, posing a significant challenge for various natural language processing tasks such as Machine Translation. Current word embedding based metaphor identification models cannot identify the exact metaphorical words within a sentence. In this paper, we propose an unsupervised learning method that identifies and interprets metaphors at word-level without any preprocessing, outperforming strong baselines in the metaphor identification task. Our model extends to interpret the identified metaphors, paraphrasing them into their literal counterparts, so that they can be better translated by machines. We evaluated this with two popular translation systems for English to Chinese, showing that our model improved the systems significantly.

KW - Metaphor Identification

KW - Metaphor Interpretation

KW - Word Embedding output vector

M3 - Conference contribution

SN - 978-1-948087-32-2

VL - 1: Long Papers

SP - 1222

EP - 1231

BT - Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics (ACL)

CY - Melbourne, Australia

ER -