@inproceedings{zhang-etal-2023-structure,
title = "Structure and Label Constrained Data Augmentation for Cross-domain Few-shot {NER}",
author = "Zhang, Jingyi and
Zhang, Ying and
Chen, Yufeng and
Xu, Jinan",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.37",
doi = "10.18653/v1/2023.findings-emnlp.37",
pages = "518--530",
abstract = "Cross-domain few-shot named entity recognition (NER) is a challenging task that aims to recognize entities in target domains with limited labeled data by leveraging relevant knowledge from source domains. However, domain gaps limit the effect of knowledge transfer and harm the performance of NER models. In this paper, we analyze those domain gaps from two new perspectives, i.e., entity annotations and entity structures and leverage word-to-tag and word-to-word relations to model them, respectively. Moreover, we propose a novel method called Structure and Label Constrained Data Augmentation (SLC-DA) for Cross-domain Few-shot NER, which novelly design a label constrained pre-train task and a structure constrained optimization objectives in the data augmentation process to generate domain-specific augmented data to help NER models smoothly transition from source to target domains. We evaluate our approach on several standard datasets and achieve state-of-the-art or competitive results, demonstrating the effectiveness of our method in cross-domain few-shot NER.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-structure">
<titleInfo>
<title>Structure and Label Constrained Data Augmentation for Cross-domain Few-shot NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-domain few-shot named entity recognition (NER) is a challenging task that aims to recognize entities in target domains with limited labeled data by leveraging relevant knowledge from source domains. However, domain gaps limit the effect of knowledge transfer and harm the performance of NER models. In this paper, we analyze those domain gaps from two new perspectives, i.e., entity annotations and entity structures and leverage word-to-tag and word-to-word relations to model them, respectively. Moreover, we propose a novel method called Structure and Label Constrained Data Augmentation (SLC-DA) for Cross-domain Few-shot NER, which novelly design a label constrained pre-train task and a structure constrained optimization objectives in the data augmentation process to generate domain-specific augmented data to help NER models smoothly transition from source to target domains. We evaluate our approach on several standard datasets and achieve state-of-the-art or competitive results, demonstrating the effectiveness of our method in cross-domain few-shot NER.</abstract>
<identifier type="citekey">zhang-etal-2023-structure</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.37</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.37</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>518</start>
<end>530</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structure and Label Constrained Data Augmentation for Cross-domain Few-shot NER
%A Zhang, Jingyi
%A Zhang, Ying
%A Chen, Yufeng
%A Xu, Jinan
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-etal-2023-structure
%X Cross-domain few-shot named entity recognition (NER) is a challenging task that aims to recognize entities in target domains with limited labeled data by leveraging relevant knowledge from source domains. However, domain gaps limit the effect of knowledge transfer and harm the performance of NER models. In this paper, we analyze those domain gaps from two new perspectives, i.e., entity annotations and entity structures and leverage word-to-tag and word-to-word relations to model them, respectively. Moreover, we propose a novel method called Structure and Label Constrained Data Augmentation (SLC-DA) for Cross-domain Few-shot NER, which novelly design a label constrained pre-train task and a structure constrained optimization objectives in the data augmentation process to generate domain-specific augmented data to help NER models smoothly transition from source to target domains. We evaluate our approach on several standard datasets and achieve state-of-the-art or competitive results, demonstrating the effectiveness of our method in cross-domain few-shot NER.
%R 10.18653/v1/2023.findings-emnlp.37
%U https://aclanthology.org/2023.findings-emnlp.37
%U https://doi.org/10.18653/v1/2023.findings-emnlp.37
%P 518-530
Markdown (Informal)
[Structure and Label Constrained Data Augmentation for Cross-domain Few-shot NER](https://aclanthology.org/2023.findings-emnlp.37) (Zhang et al., Findings 2023)
ACL