@inproceedings{liang-etal-2024-selp,
title = "{SELP}: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification",
author = "Liang, Wenxin and
Zhang, Tingyu and
Liu, Han and
Zhang, Feng",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.579",
pages = "9732--9741",
abstract = "The meta-learning paradigm has demonstrated significant effectiveness in few-shot text classification. Currently, numerous efforts are grounded in metric-based learning, utilizing textual feature vectors for classification, with a common emphasis on enlarging inter-class distances to achieve improved classification effectiveness. However, many methods predominantly focus on enhancing the separation of prototypes without taking the semantic relationships between prototypes and class clusters into consideration. This oversight results in incomplete and inaccurate encoding of prototypes within the semantic space, affecting the generality of the learned metric space. In this paper, we propose the utilization of $\textbf{S}$emantically $\textbf{E}$nhanced $\textbf{L}$abels for calibrating class $\textbf{P}$rototypes ($\textbf{SELP}$), thereby obtaining prototypes that are more separated and semantically accurate. Additionally, we have devised a center loss to enhance intra-class compactness, coupled with the introduction of a simulated label distribution method to address the overfitting problem. Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms baselines significantly. Our code is available at https://github.com/tttyyyzzz-zty/SELP.git.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2024-selp">
<titleInfo>
<title>SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenxin</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Zhang</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>Findings of the Association for Computational Linguistics ACL 2024</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 and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The meta-learning paradigm has demonstrated significant effectiveness in few-shot text classification. Currently, numerous efforts are grounded in metric-based learning, utilizing textual feature vectors for classification, with a common emphasis on enlarging inter-class distances to achieve improved classification effectiveness. However, many methods predominantly focus on enhancing the separation of prototypes without taking the semantic relationships between prototypes and class clusters into consideration. This oversight results in incomplete and inaccurate encoding of prototypes within the semantic space, affecting the generality of the learned metric space. In this paper, we propose the utilization of Semantically Enhanced Labels for calibrating class Prototypes (SELP), thereby obtaining prototypes that are more separated and semantically accurate. Additionally, we have devised a center loss to enhance intra-class compactness, coupled with the introduction of a simulated label distribution method to address the overfitting problem. Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms baselines significantly. Our code is available at https://github.com/tttyyyzzz-zty/SELP.git.</abstract>
<identifier type="citekey">liang-etal-2024-selp</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.579</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9732</start>
<end>9741</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification
%A Liang, Wenxin
%A Zhang, Tingyu
%A Liu, Han
%A Zhang, Feng
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F liang-etal-2024-selp
%X The meta-learning paradigm has demonstrated significant effectiveness in few-shot text classification. Currently, numerous efforts are grounded in metric-based learning, utilizing textual feature vectors for classification, with a common emphasis on enlarging inter-class distances to achieve improved classification effectiveness. However, many methods predominantly focus on enhancing the separation of prototypes without taking the semantic relationships between prototypes and class clusters into consideration. This oversight results in incomplete and inaccurate encoding of prototypes within the semantic space, affecting the generality of the learned metric space. In this paper, we propose the utilization of Semantically Enhanced Labels for calibrating class Prototypes (SELP), thereby obtaining prototypes that are more separated and semantically accurate. Additionally, we have devised a center loss to enhance intra-class compactness, coupled with the introduction of a simulated label distribution method to address the overfitting problem. Extensive experiments on eight few-shot text classification datasets show that the proposed method outperforms baselines significantly. Our code is available at https://github.com/tttyyyzzz-zty/SELP.git.
%U https://aclanthology.org/2024.findings-acl.579
%P 9732-9741
Markdown (Informal)
[SELP: A Semantically-Driven Approach for Separated and Accurate Class Prototypes in Few-Shot Text Classification](https://aclanthology.org/2024.findings-acl.579) (Liang et al., Findings 2024)
ACL