<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-li-2023-scdner">
    <titleInfo>
        <title>ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ying</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qi</namePart>
        <namePart type="family">Li</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>Document-level NER approaches use global information via word-based key-value memory for accurate and consistent predictions. However, such global information on word level can introduce noise when the same word appears in different token sequences and has different labels. This work proposes a two-stage document-level NER model, ScdNER, for more accurate and consistent predictions via adaptive span-level global feature fusion. In the first stage, ScdNER trains a binary classifier to predict if a token sequence is an entity with a probability. Via a span-based key-value memory, the probabilities are further used to obtain the entity’s global features with reduced impact of non-entity sequences. The second stage predicts the entity types using a gate mechanism to balance its local and global information, leading to adaptive global feature fusion. Experiments on benchmark datasets from scientific, biomedical, and general domains show the effectiveness of the proposed methods.</abstract>
    <identifier type="citekey">wei-li-2023-scdner</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.970</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.970</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>15677</start>
            <end>15685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition
%A Wei, Ying
%A Li, Qi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F wei-li-2023-scdner
%X Document-level NER approaches use global information via word-based key-value memory for accurate and consistent predictions. However, such global information on word level can introduce noise when the same word appears in different token sequences and has different labels. This work proposes a two-stage document-level NER model, ScdNER, for more accurate and consistent predictions via adaptive span-level global feature fusion. In the first stage, ScdNER trains a binary classifier to predict if a token sequence is an entity with a probability. Via a span-based key-value memory, the probabilities are further used to obtain the entity’s global features with reduced impact of non-entity sequences. The second stage predicts the entity types using a gate mechanism to balance its local and global information, leading to adaptive global feature fusion. Experiments on benchmark datasets from scientific, biomedical, and general domains show the effectiveness of the proposed methods.
%R 10.18653/v1/2023.emnlp-main.970
%U https://aclanthology.org/2023.emnlp-main.970
%U https://doi.org/10.18653/v1/2023.emnlp-main.970
%P 15677-15685

Markdown (Informal)

[ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition](https://aclanthology.org/2023.emnlp-main.970) (Wei & Li, EMNLP 2023)

• ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition (Wei & Li, EMNLP 2023)

ACL

• Ying Wei and Qi Li. 2023. ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15677–15685, Singapore. Association for Computational Linguistics.