@inproceedings{yeginbergen-etal-2024-argument,
title = "Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques",
author = "Yeginbergen, Anar and
Oronoz, Maite and
Agerri, Rodrigo",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.628/",
doi = "10.18653/v1/2024.acl-long.628",
pages = "11687--11699",
abstract = "Recent research on sequence labelling has been exploring different strategies to mitigate the lack of manually annotated data for the large majority of the world languages. Among others, the most successful approaches have been based on (i) the crosslingual transfer capabilities of multilingual pre-trained language models (model-transfer), (ii) data translation and label projection (data-transfer) and (iii), prompt-based learning by reusing the mask objective to exploit the few-shot capabilities of pre-trained language models (few-shot). Previous work seems to conclude that model-transfer outperform data-transfer methods and that few-shot techniques based on prompting are superior to updating the model`s weights via fine-tuning. In this paper we empirically demonstrate that, for Argument Mining, a sequence labelling task which requires the detection of long and complex discourse structures, previous insights on crosslingual transfer or few-shot learning do not apply. Contrary to previous work, we show that for Argument Mining data-transfer obtains better results than model-transfer and that fine-tuning outperforms few-shot methods. Regarding the former, the domain of the dataset used for data-transfer seems to be a deciding factor, while, for few-shot, the type of task (length and complexity of the sequence spans) and sampling method proves to be crucial."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yeginbergen-etal-2024-argument">
<titleInfo>
<title>Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anar</namePart>
<namePart type="family">Yeginbergen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Oronoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Agerri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research on sequence labelling has been exploring different strategies to mitigate the lack of manually annotated data for the large majority of the world languages. Among others, the most successful approaches have been based on (i) the crosslingual transfer capabilities of multilingual pre-trained language models (model-transfer), (ii) data translation and label projection (data-transfer) and (iii), prompt-based learning by reusing the mask objective to exploit the few-shot capabilities of pre-trained language models (few-shot). Previous work seems to conclude that model-transfer outperform data-transfer methods and that few-shot techniques based on prompting are superior to updating the model‘s weights via fine-tuning. In this paper we empirically demonstrate that, for Argument Mining, a sequence labelling task which requires the detection of long and complex discourse structures, previous insights on crosslingual transfer or few-shot learning do not apply. Contrary to previous work, we show that for Argument Mining data-transfer obtains better results than model-transfer and that fine-tuning outperforms few-shot methods. Regarding the former, the domain of the dataset used for data-transfer seems to be a deciding factor, while, for few-shot, the type of task (length and complexity of the sequence spans) and sampling method proves to be crucial.</abstract>
<identifier type="citekey">yeginbergen-etal-2024-argument</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.628</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.628/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11687</start>
<end>11699</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques
%A Yeginbergen, Anar
%A Oronoz, Maite
%A Agerri, Rodrigo
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F yeginbergen-etal-2024-argument
%X Recent research on sequence labelling has been exploring different strategies to mitigate the lack of manually annotated data for the large majority of the world languages. Among others, the most successful approaches have been based on (i) the crosslingual transfer capabilities of multilingual pre-trained language models (model-transfer), (ii) data translation and label projection (data-transfer) and (iii), prompt-based learning by reusing the mask objective to exploit the few-shot capabilities of pre-trained language models (few-shot). Previous work seems to conclude that model-transfer outperform data-transfer methods and that few-shot techniques based on prompting are superior to updating the model‘s weights via fine-tuning. In this paper we empirically demonstrate that, for Argument Mining, a sequence labelling task which requires the detection of long and complex discourse structures, previous insights on crosslingual transfer or few-shot learning do not apply. Contrary to previous work, we show that for Argument Mining data-transfer obtains better results than model-transfer and that fine-tuning outperforms few-shot methods. Regarding the former, the domain of the dataset used for data-transfer seems to be a deciding factor, while, for few-shot, the type of task (length and complexity of the sequence spans) and sampling method proves to be crucial.
%R 10.18653/v1/2024.acl-long.628
%U https://aclanthology.org/2024.luhme-long.628/
%U https://doi.org/10.18653/v1/2024.acl-long.628
%P 11687-11699
Markdown (Informal)
[Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques](https://aclanthology.org/2024.luhme-long.628/) (Yeginbergen et al., ACL 2024)
ACL