@inproceedings{ma-etal-2023-coarse,
title = "Coarse-to-fine Few-shot Learning for Named Entity Recognition",
author = "Ma, Ruotian and
Lin, Zhang and
Chen, Xuanting and
Zhou, Xin and
Wang, Junzhe and
Gui, Tao and
Zhang, Qi and
Gao, Xiang and
Chen, Yun Wen",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.253/",
doi = "10.18653/v1/2023.findings-acl.253",
pages = "4115--4129",
abstract = "Recently, Few-shot Named Entity Recognition has received wide attention with the growing need for NER models to learn new classes with minimized annotation costs. However, one common yet understudied situation is to transfer a model trained with coarse-grained classes to recognize fine-grained classes, such as separating a product category into sub-classes. We find that existing few-shot NER solutions are not suitable for such a situation since they do not consider the sub-class discrimination during coarse training and various granularity of new classes during few-shot learning. In this work, we introduce the Coarse-to-fine Few-shot NER (C2FNER) task and propose an effective solution. Specifically, during coarse training, we propose a cluster-based prototype margin loss to learn group-wise discriminative representations, so as to benefit fine-grained learning. Targeting various granularity of new classes, we separate the coarse classes into extra-fine clusters and propose a novel prototype retrieval and bootstrapping algorithm to retrieve representative clusters for each fine class. We then adopt a mixture prototype loss to efficiently learn the representations of fine classes. We conduct experiments on both in-domain and cross-domain C2FNER settings with various target granularity, and the proposed method shows superior performance over the baseline methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2023-coarse">
<titleInfo>
<title>Coarse-to-fine Few-shot Learning for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruotian</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanting</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junzhe</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="given">Wen</namePart>
<namePart type="family">Chen</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>Findings of the Association for Computational Linguistics: ACL 2023</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>Recently, Few-shot Named Entity Recognition has received wide attention with the growing need for NER models to learn new classes with minimized annotation costs. However, one common yet understudied situation is to transfer a model trained with coarse-grained classes to recognize fine-grained classes, such as separating a product category into sub-classes. We find that existing few-shot NER solutions are not suitable for such a situation since they do not consider the sub-class discrimination during coarse training and various granularity of new classes during few-shot learning. In this work, we introduce the Coarse-to-fine Few-shot NER (C2FNER) task and propose an effective solution. Specifically, during coarse training, we propose a cluster-based prototype margin loss to learn group-wise discriminative representations, so as to benefit fine-grained learning. Targeting various granularity of new classes, we separate the coarse classes into extra-fine clusters and propose a novel prototype retrieval and bootstrapping algorithm to retrieve representative clusters for each fine class. We then adopt a mixture prototype loss to efficiently learn the representations of fine classes. We conduct experiments on both in-domain and cross-domain C2FNER settings with various target granularity, and the proposed method shows superior performance over the baseline methods.</abstract>
<identifier type="citekey">ma-etal-2023-coarse</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.253</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.253/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>4115</start>
<end>4129</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coarse-to-fine Few-shot Learning for Named Entity Recognition
%A Ma, Ruotian
%A Lin, Zhang
%A Chen, Xuanting
%A Zhou, Xin
%A Wang, Junzhe
%A Gui, Tao
%A Zhang, Qi
%A Gao, Xiang
%A Chen, Yun Wen
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ma-etal-2023-coarse
%X Recently, Few-shot Named Entity Recognition has received wide attention with the growing need for NER models to learn new classes with minimized annotation costs. However, one common yet understudied situation is to transfer a model trained with coarse-grained classes to recognize fine-grained classes, such as separating a product category into sub-classes. We find that existing few-shot NER solutions are not suitable for such a situation since they do not consider the sub-class discrimination during coarse training and various granularity of new classes during few-shot learning. In this work, we introduce the Coarse-to-fine Few-shot NER (C2FNER) task and propose an effective solution. Specifically, during coarse training, we propose a cluster-based prototype margin loss to learn group-wise discriminative representations, so as to benefit fine-grained learning. Targeting various granularity of new classes, we separate the coarse classes into extra-fine clusters and propose a novel prototype retrieval and bootstrapping algorithm to retrieve representative clusters for each fine class. We then adopt a mixture prototype loss to efficiently learn the representations of fine classes. We conduct experiments on both in-domain and cross-domain C2FNER settings with various target granularity, and the proposed method shows superior performance over the baseline methods.
%R 10.18653/v1/2023.findings-acl.253
%U https://aclanthology.org/2023.findings-acl.253/
%U https://doi.org/10.18653/v1/2023.findings-acl.253
%P 4115-4129
Markdown (Informal)
[Coarse-to-fine Few-shot Learning for Named Entity Recognition](https://aclanthology.org/2023.findings-acl.253/) (Ma et al., Findings 2023)
ACL
- Ruotian Ma, Zhang Lin, Xuanting Chen, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, and Yun Wen Chen. 2023. Coarse-to-fine Few-shot Learning for Named Entity Recognition. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4115–4129, Toronto, Canada. Association for Computational Linguistics.