@inproceedings{xie-li-2024-discriminative-language,
title = "Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification",
author = "Xie, Zhipeng and
Li, Yahe",
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.445",
pages = "4968--4977",
abstract = "A successful prompt-based finetuning method should have three prerequisites: task compatibility, input compatibility, and evidence abundance. Bearing this belief in mind, this paper designs a novel prompt-based method (called DLM-SCS) for few-shot text classification, which utilizes the discriminative language model ELECTRA that is pretrained to distinguish whether a token is original or replaced. The method is built upon the intuitive idea that the prompt instantiated with the true label should have higher semantic consistency score than other prompts with false labels. Since a prompt usually consists of several components (or parts), its semantic consistency can be decomposed accordingly, which means each part can provide information for semantic consistency discrimination. The semantic consistency of each component is then computed by making use of the pretrained ELECTRA model, where no extra parameters get introduced. Extensive experiments have shown that our model outperforms several state-of-the-art prompt-based few-shot methods on 10 widely-used text classification tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-li-2024-discriminative-language">
<titleInfo>
<title>Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yahe</namePart>
<namePart type="family">Li</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>A successful prompt-based finetuning method should have three prerequisites: task compatibility, input compatibility, and evidence abundance. Bearing this belief in mind, this paper designs a novel prompt-based method (called DLM-SCS) for few-shot text classification, which utilizes the discriminative language model ELECTRA that is pretrained to distinguish whether a token is original or replaced. The method is built upon the intuitive idea that the prompt instantiated with the true label should have higher semantic consistency score than other prompts with false labels. Since a prompt usually consists of several components (or parts), its semantic consistency can be decomposed accordingly, which means each part can provide information for semantic consistency discrimination. The semantic consistency of each component is then computed by making use of the pretrained ELECTRA model, where no extra parameters get introduced. Extensive experiments have shown that our model outperforms several state-of-the-art prompt-based few-shot methods on 10 widely-used text classification tasks.</abstract>
<identifier type="citekey">xie-li-2024-discriminative-language</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.445</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4968</start>
<end>4977</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification
%A Xie, Zhipeng
%A Li, Yahe
%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 xie-li-2024-discriminative-language
%X A successful prompt-based finetuning method should have three prerequisites: task compatibility, input compatibility, and evidence abundance. Bearing this belief in mind, this paper designs a novel prompt-based method (called DLM-SCS) for few-shot text classification, which utilizes the discriminative language model ELECTRA that is pretrained to distinguish whether a token is original or replaced. The method is built upon the intuitive idea that the prompt instantiated with the true label should have higher semantic consistency score than other prompts with false labels. Since a prompt usually consists of several components (or parts), its semantic consistency can be decomposed accordingly, which means each part can provide information for semantic consistency discrimination. The semantic consistency of each component is then computed by making use of the pretrained ELECTRA model, where no extra parameters get introduced. Extensive experiments have shown that our model outperforms several state-of-the-art prompt-based few-shot methods on 10 widely-used text classification tasks.
%U https://aclanthology.org/2024.lrec-main.445
%P 4968-4977
Markdown (Informal)
[Discriminative Language Model as Semantic Consistency Scorer for Prompt-based Few-Shot Text Classification](https://aclanthology.org/2024.lrec-main.445) (Xie & Li, LREC-COLING 2024)
ACL