@inproceedings{boisson-etal-2023-construction,
title = "Construction Artifacts in Metaphor Identification Datasets",
author = "Boisson, Joanne and
Espinosa-Anke, Luis and
Camacho-Collados, Jose",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.406",
doi = "10.18653/v1/2023.emnlp-main.406",
pages = "6581--6590",
abstract = "Metaphor identification aims at understanding whether a given expression is used figuratively in context. However, in this paper we show how existing metaphor identification datasets can be gamed by fully ignoring the potential metaphorical expression or the context in which it occurs. We test this hypothesis in a variety of datasets and settings, and show that metaphor identification systems based on language models without complete information can be competitive with those using the full context. This is due to the construction procedures to build such datasets, which introduce unwanted biases for positive and negative classes. Finally, we test the same hypothesis on datasets that are carefully sampled from natural corpora and where this bias is not present, making these datasets more challenging and reliable.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boisson-etal-2023-construction">
<titleInfo>
<title>Construction Artifacts in Metaphor Identification Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joanne</namePart>
<namePart type="family">Boisson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Espinosa-Anke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-Collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Metaphor identification aims at understanding whether a given expression is used figuratively in context. However, in this paper we show how existing metaphor identification datasets can be gamed by fully ignoring the potential metaphorical expression or the context in which it occurs. We test this hypothesis in a variety of datasets and settings, and show that metaphor identification systems based on language models without complete information can be competitive with those using the full context. This is due to the construction procedures to build such datasets, which introduce unwanted biases for positive and negative classes. Finally, we test the same hypothesis on datasets that are carefully sampled from natural corpora and where this bias is not present, making these datasets more challenging and reliable.</abstract>
<identifier type="citekey">boisson-etal-2023-construction</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.406</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.406</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6581</start>
<end>6590</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Construction Artifacts in Metaphor Identification Datasets
%A Boisson, Joanne
%A Espinosa-Anke, Luis
%A Camacho-Collados, Jose
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F boisson-etal-2023-construction
%X Metaphor identification aims at understanding whether a given expression is used figuratively in context. However, in this paper we show how existing metaphor identification datasets can be gamed by fully ignoring the potential metaphorical expression or the context in which it occurs. We test this hypothesis in a variety of datasets and settings, and show that metaphor identification systems based on language models without complete information can be competitive with those using the full context. This is due to the construction procedures to build such datasets, which introduce unwanted biases for positive and negative classes. Finally, we test the same hypothesis on datasets that are carefully sampled from natural corpora and where this bias is not present, making these datasets more challenging and reliable.
%R 10.18653/v1/2023.emnlp-main.406
%U https://aclanthology.org/2023.emnlp-main.406
%U https://doi.org/10.18653/v1/2023.emnlp-main.406
%P 6581-6590
Markdown (Informal)
[Construction Artifacts in Metaphor Identification Datasets](https://aclanthology.org/2023.emnlp-main.406) (Boisson et al., EMNLP 2023)
ACL
- Joanne Boisson, Luis Espinosa-Anke, and Jose Camacho-Collados. 2023. Construction Artifacts in Metaphor Identification Datasets. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6581–6590, Singapore. Association for Computational Linguistics.