@inproceedings{hulsing-schulte-im-walde-2024-cross,
title = "Cross-Lingual Metaphor Detection for Low-Resource Languages",
author = {H{\"u}lsing, Anna and
Schulte Im Walde, Sabine},
editor = "Ghosh, Debanjan and
Muresan, Smaranda and
Feldman, Anna and
Chakrabarty, Tuhin and
Liu, Emmy",
booktitle = "Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.figlang-1.4",
doi = "10.18653/v1/2024.figlang-1.4",
pages = "22--34",
abstract = "Research on metaphor detection (MD) in a multilingual setup has recently gained momentum. As for many tasks, it is however unclear how the amount of data used to pretrain large language models affects the performance, and whether non-neural models might provide a reasonable alternative, especially for MD in low-resource languages. This paper compares neural and non-neural cross-lingual models for English as the source language and Russian, German and Latin as target languages. In a series of experiments we show that the neural cross-lingual adapter architecture MAD-X performs best across target languages. Zero-shot classification with mBERT achieves decent results above the majority baseline, while few-shot classification with mBERT heavily depends on shot-selection, which is inconvenient in a cross-lingual setup where no validation data for the target language exists. The non-neural model, a random forest classifier with conceptual features, is outperformed by the neural models. Overall, we recommend MAD-X for metaphor detection not only in high-resource but also in low-resource scenarios regarding the amounts of pretraining data for mBERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hulsing-schulte-im-walde-2024-cross">
<titleInfo>
<title>Cross-Lingual Metaphor Detection for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Hülsing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Schulte Im Walde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuhin</namePart>
<namePart type="family">Chakrabarty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research on metaphor detection (MD) in a multilingual setup has recently gained momentum. As for many tasks, it is however unclear how the amount of data used to pretrain large language models affects the performance, and whether non-neural models might provide a reasonable alternative, especially for MD in low-resource languages. This paper compares neural and non-neural cross-lingual models for English as the source language and Russian, German and Latin as target languages. In a series of experiments we show that the neural cross-lingual adapter architecture MAD-X performs best across target languages. Zero-shot classification with mBERT achieves decent results above the majority baseline, while few-shot classification with mBERT heavily depends on shot-selection, which is inconvenient in a cross-lingual setup where no validation data for the target language exists. The non-neural model, a random forest classifier with conceptual features, is outperformed by the neural models. Overall, we recommend MAD-X for metaphor detection not only in high-resource but also in low-resource scenarios regarding the amounts of pretraining data for mBERT.</abstract>
<identifier type="citekey">hulsing-schulte-im-walde-2024-cross</identifier>
<identifier type="doi">10.18653/v1/2024.figlang-1.4</identifier>
<location>
<url>https://aclanthology.org/2024.figlang-1.4</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>22</start>
<end>34</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Metaphor Detection for Low-Resource Languages
%A Hülsing, Anna
%A Schulte Im Walde, Sabine
%Y Ghosh, Debanjan
%Y Muresan, Smaranda
%Y Feldman, Anna
%Y Chakrabarty, Tuhin
%Y Liu, Emmy
%S Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico (Hybrid)
%F hulsing-schulte-im-walde-2024-cross
%X Research on metaphor detection (MD) in a multilingual setup has recently gained momentum. As for many tasks, it is however unclear how the amount of data used to pretrain large language models affects the performance, and whether non-neural models might provide a reasonable alternative, especially for MD in low-resource languages. This paper compares neural and non-neural cross-lingual models for English as the source language and Russian, German and Latin as target languages. In a series of experiments we show that the neural cross-lingual adapter architecture MAD-X performs best across target languages. Zero-shot classification with mBERT achieves decent results above the majority baseline, while few-shot classification with mBERT heavily depends on shot-selection, which is inconvenient in a cross-lingual setup where no validation data for the target language exists. The non-neural model, a random forest classifier with conceptual features, is outperformed by the neural models. Overall, we recommend MAD-X for metaphor detection not only in high-resource but also in low-resource scenarios regarding the amounts of pretraining data for mBERT.
%R 10.18653/v1/2024.figlang-1.4
%U https://aclanthology.org/2024.figlang-1.4
%U https://doi.org/10.18653/v1/2024.figlang-1.4
%P 22-34
Markdown (Informal)
[Cross-Lingual Metaphor Detection for Low-Resource Languages](https://aclanthology.org/2024.figlang-1.4) (Hülsing & Schulte Im Walde, Fig-Lang-WS 2024)
ACL