<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2022-label">
    <titleInfo>
        <title>A Label-Aware Autoregressive Framework for Cross-Domain NER</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinpeng</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">He</namePart>
        <namePart type="family">Zhao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dan</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiang</namePart>
        <namePart type="family">Wan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tsung-Hui</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="given">Vladimir</namePart>
            <namePart type="family">Meza Ruiz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Cross-domain named entity recognition (NER) aims to borrow the entity information from the source domain to help the entity recognition in the target domain with limited labeled data. Despite the promising performance of existing approaches, most of them focus on reducing the discrepancy of token representation between source and target domains, while the transfer of the valuable label information is often not explicitly considered or even ignored. Therefore, we propose a novel autoregressive framework to advance cross-domain NER by first enhancing the relationship between labels and tokens and then further improving the transferability of label information. Specifically, we associate each label with an embedding vector, and for each token, we utilize a bidirectional LSTM (Bi-LSTM) to encode the labels of its previous tokens for modeling internal context information and label dependence. Afterward, we propose a Bi-Attention module that merges the token representation from a pre-trained model and the label features from the Bi-LSTM as the label-aware information, which is concatenated to the token representation to facilitate cross-domain NER. In doing so, label information contained in the embedding vectors can be effectively transferred to the target domain, and Bi-LSTM can further model the label relationship among different domains by pre-train and then fine-tune setting. Experimental results on several datasets confirm the effectiveness of our model, where our model achieves significant improvements over the state of the arts.</abstract>
    <identifier type="citekey">hu-etal-2022-label</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-naacl.171</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-naacl.171</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>2222</start>
            <end>2232</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Label-Aware Autoregressive Framework for Cross-Domain NER
%A Hu, Jinpeng
%A Zhao, He
%A Guo, Dan
%A Wan, Xiang
%A Chang, Tsung-Hui
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F hu-etal-2022-label
%X Cross-domain named entity recognition (NER) aims to borrow the entity information from the source domain to help the entity recognition in the target domain with limited labeled data. Despite the promising performance of existing approaches, most of them focus on reducing the discrepancy of token representation between source and target domains, while the transfer of the valuable label information is often not explicitly considered or even ignored. Therefore, we propose a novel autoregressive framework to advance cross-domain NER by first enhancing the relationship between labels and tokens and then further improving the transferability of label information. Specifically, we associate each label with an embedding vector, and for each token, we utilize a bidirectional LSTM (Bi-LSTM) to encode the labels of its previous tokens for modeling internal context information and label dependence. Afterward, we propose a Bi-Attention module that merges the token representation from a pre-trained model and the label features from the Bi-LSTM as the label-aware information, which is concatenated to the token representation to facilitate cross-domain NER. In doing so, label information contained in the embedding vectors can be effectively transferred to the target domain, and Bi-LSTM can further model the label relationship among different domains by pre-train and then fine-tune setting. Experimental results on several datasets confirm the effectiveness of our model, where our model achieves significant improvements over the state of the arts.
%R 10.18653/v1/2022.findings-naacl.171
%U https://aclanthology.org/2022.findings-naacl.171
%U https://doi.org/10.18653/v1/2022.findings-naacl.171
%P 2222-2232

Markdown (Informal)

[A Label-Aware Autoregressive Framework for Cross-Domain NER](https://aclanthology.org/2022.findings-naacl.171) (Hu et al., Findings 2022)

• A Label-Aware Autoregressive Framework for Cross-Domain NER (Hu et al., Findings 2022)

ACL

• Jinpeng Hu, He Zhao, Dan Guo, Xiang Wan, and Tsung-Hui Chang. 2022. A Label-Aware Autoregressive Framework for Cross-Domain NER. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2222–2232, Seattle, United States. Association for Computational Linguistics.