@inproceedings{nguyen-etal-2024-enhancing-shot,
title = "Enhancing Few-Shot Topic Classification with Verbalizers. a Study on Automatic Verbalizer and Ensemble Methods",
author = "Nguyen, Quang Anh and
Tomeh, Nadi and
Lebbah, Mustapha and
Charnois, Thierry and
Azzag, Hanene and
Cordoba Mu{\~n}oz, Santiago",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.527",
pages = "5956--5965",
abstract = "As pretrained language model emerge and consistently develop, prompt-based training has become a well-studied paradigm to improve the exploitation of models for many natural language processing tasks. Furthermore, prompting demonstrates great performance compared to conventional fine-tuning in scenarios with limited annotated data, such as zero-shot or few-shot situations. Verbalizers are crucial in this context, as they help interpret masked word distributions generated by language models into output predictions. This study introduces a benchmarking approach to assess three common baselines of verbalizers for topic classification in few-shot learning scenarios. Additionally, we find that increasing the number of label words for automatic label word searching enhances model performance. Moreover, we investigate the effectiveness of template assembling with various aggregation strategies to develop stronger classifiers that outperform models trained with individual templates. Our approach achieves comparable results to prior research while using significantly fewer resources. Our code is available at https://github.com/quang-anh-nguyen/verbalizer{\_}benchmark.git.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2024-enhancing-shot">
<titleInfo>
<title>Enhancing Few-Shot Topic Classification with Verbalizers. a Study on Automatic Verbalizer and Ensemble Methods</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quang</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mustapha</namePart>
<namePart type="family">Lebbah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Charnois</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanene</namePart>
<namePart type="family">Azzag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Cordoba Muñoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As pretrained language model emerge and consistently develop, prompt-based training has become a well-studied paradigm to improve the exploitation of models for many natural language processing tasks. Furthermore, prompting demonstrates great performance compared to conventional fine-tuning in scenarios with limited annotated data, such as zero-shot or few-shot situations. Verbalizers are crucial in this context, as they help interpret masked word distributions generated by language models into output predictions. This study introduces a benchmarking approach to assess three common baselines of verbalizers for topic classification in few-shot learning scenarios. Additionally, we find that increasing the number of label words for automatic label word searching enhances model performance. Moreover, we investigate the effectiveness of template assembling with various aggregation strategies to develop stronger classifiers that outperform models trained with individual templates. Our approach achieves comparable results to prior research while using significantly fewer resources. Our code is available at https://github.com/quang-anh-nguyen/verbalizer_benchmark.git.</abstract>
<identifier type="citekey">nguyen-etal-2024-enhancing-shot</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.527</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5956</start>
<end>5965</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Few-Shot Topic Classification with Verbalizers. a Study on Automatic Verbalizer and Ensemble Methods
%A Nguyen, Quang Anh
%A Tomeh, Nadi
%A Lebbah, Mustapha
%A Charnois, Thierry
%A Azzag, Hanene
%A Cordoba Muñoz, Santiago
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nguyen-etal-2024-enhancing-shot
%X As pretrained language model emerge and consistently develop, prompt-based training has become a well-studied paradigm to improve the exploitation of models for many natural language processing tasks. Furthermore, prompting demonstrates great performance compared to conventional fine-tuning in scenarios with limited annotated data, such as zero-shot or few-shot situations. Verbalizers are crucial in this context, as they help interpret masked word distributions generated by language models into output predictions. This study introduces a benchmarking approach to assess three common baselines of verbalizers for topic classification in few-shot learning scenarios. Additionally, we find that increasing the number of label words for automatic label word searching enhances model performance. Moreover, we investigate the effectiveness of template assembling with various aggregation strategies to develop stronger classifiers that outperform models trained with individual templates. Our approach achieves comparable results to prior research while using significantly fewer resources. Our code is available at https://github.com/quang-anh-nguyen/verbalizer_benchmark.git.
%U https://aclanthology.org/2024.lrec-main.527
%P 5956-5965
Markdown (Informal)
[Enhancing Few-Shot Topic Classification with Verbalizers. a Study on Automatic Verbalizer and Ensemble Methods](https://aclanthology.org/2024.lrec-main.527) (Nguyen et al., LREC-COLING 2024)
ACL