@inproceedings{lei-etal-2023-tart,
title = "{TART}: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation",
author = "Lei, Shuo and
Zhang, Xuchao and
He, Jianfeng and
Chen, Fanglan and
Lu, Chang-Tien",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.617",
doi = "10.18653/v1/2023.acl-long.617",
pages = "11014--11026",
abstract = "Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4{\%} and 5.4{\%} in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lei-etal-2023-tart">
<titleInfo>
<title>TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuchao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianfeng</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanglan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang-Tien</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4% and 5.4% in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.</abstract>
<identifier type="citekey">lei-etal-2023-tart</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.617</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.617</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11014</start>
<end>11026</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation
%A Lei, Shuo
%A Zhang, Xuchao
%A He, Jianfeng
%A Chen, Fanglan
%A Lu, Chang-Tien
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F lei-etal-2023-tart
%X Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4% and 5.4% in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.
%R 10.18653/v1/2023.acl-long.617
%U https://aclanthology.org/2023.acl-long.617
%U https://doi.org/10.18653/v1/2023.acl-long.617
%P 11014-11026
Markdown (Informal)
[TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation](https://aclanthology.org/2023.acl-long.617) (Lei et al., ACL 2023)
ACL