@inproceedings{zhang-etal-2021-multimet,
title = "{M}ulti{MET}: A Multimodal Dataset for Metaphor Understanding",
author = "Zhang, Dongyu and
Zhang, Minghao and
Zhang, Heting and
Yang, Liang and
Lin, Hongfei",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.249",
doi = "10.18653/v1/2021.acl-long.249",
pages = "3214--3225",
abstract = "Metaphor involves not only a linguistic phenomenon, but also a cognitive phenomenon structuring human thought, which makes understanding it challenging. As a means of cognition, metaphor is rendered by more than texts alone, and multimodal information in which vision/audio content is integrated with the text can play an important role in expressing and understanding metaphor. However, previous metaphor processing and understanding has focused on texts, partly due to the unavailability of large-scale datasets with ground truth labels of multimodal metaphor. In this paper, we introduce MultiMET, a novel multimodal metaphor dataset to facilitate understanding metaphorical information from multimodal text and image. It contains 10,437 text-image pairs from a range of sources with multimodal annotations of the occurrence of metaphors, domain relations, sentiments metaphors convey, and author intents. MultiMET opens the door to automatic metaphor understanding by investigating multimodal cues and their interplay. Moreover, we propose a range of strong baselines and show the importance of combining multimodal cues for metaphor understanding. MultiMET will be released publicly for research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2021-multimet">
<titleInfo>
<title>MultiMET: A Multimodal Dataset for Metaphor Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heting</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Metaphor involves not only a linguistic phenomenon, but also a cognitive phenomenon structuring human thought, which makes understanding it challenging. As a means of cognition, metaphor is rendered by more than texts alone, and multimodal information in which vision/audio content is integrated with the text can play an important role in expressing and understanding metaphor. However, previous metaphor processing and understanding has focused on texts, partly due to the unavailability of large-scale datasets with ground truth labels of multimodal metaphor. In this paper, we introduce MultiMET, a novel multimodal metaphor dataset to facilitate understanding metaphorical information from multimodal text and image. It contains 10,437 text-image pairs from a range of sources with multimodal annotations of the occurrence of metaphors, domain relations, sentiments metaphors convey, and author intents. MultiMET opens the door to automatic metaphor understanding by investigating multimodal cues and their interplay. Moreover, we propose a range of strong baselines and show the importance of combining multimodal cues for metaphor understanding. MultiMET will be released publicly for research.</abstract>
<identifier type="citekey">zhang-etal-2021-multimet</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.249</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.249</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>3214</start>
<end>3225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiMET: A Multimodal Dataset for Metaphor Understanding
%A Zhang, Dongyu
%A Zhang, Minghao
%A Zhang, Heting
%A Yang, Liang
%A Lin, Hongfei
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F zhang-etal-2021-multimet
%X Metaphor involves not only a linguistic phenomenon, but also a cognitive phenomenon structuring human thought, which makes understanding it challenging. As a means of cognition, metaphor is rendered by more than texts alone, and multimodal information in which vision/audio content is integrated with the text can play an important role in expressing and understanding metaphor. However, previous metaphor processing and understanding has focused on texts, partly due to the unavailability of large-scale datasets with ground truth labels of multimodal metaphor. In this paper, we introduce MultiMET, a novel multimodal metaphor dataset to facilitate understanding metaphorical information from multimodal text and image. It contains 10,437 text-image pairs from a range of sources with multimodal annotations of the occurrence of metaphors, domain relations, sentiments metaphors convey, and author intents. MultiMET opens the door to automatic metaphor understanding by investigating multimodal cues and their interplay. Moreover, we propose a range of strong baselines and show the importance of combining multimodal cues for metaphor understanding. MultiMET will be released publicly for research.
%R 10.18653/v1/2021.acl-long.249
%U https://aclanthology.org/2021.acl-long.249
%U https://doi.org/10.18653/v1/2021.acl-long.249
%P 3214-3225
Markdown (Informal)
[MultiMET: A Multimodal Dataset for Metaphor Understanding](https://aclanthology.org/2021.acl-long.249) (Zhang et al., ACL-IJCNLP 2021)
ACL
- Dongyu Zhang, Minghao Zhang, Heting Zhang, Liang Yang, and Hongfei Lin. 2021. MultiMET: A Multimodal Dataset for Metaphor Understanding. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3214–3225, Online. Association for Computational Linguistics.