<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aly-etal-2021-leveraging">
    <titleInfo>
        <title>Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rami</namePart>
        <namePart type="family">Aly</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">Vlachos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryan</namePart>
        <namePart type="family">McDonald</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-aug</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for the target entity classes during training. Zero-shot learning approaches address this issue by learning models from classes with training data that can predict classes without it. This paper presents the first approach for zero-shot NERC, introducing novel architectures that leverage the fact that textual descriptions for many entity classes occur naturally. We address the zero-shot NERC specific challenge that the not-an-entity class is not well defined as different entity classes are considered in training and testing. For evaluation, we adapt two datasets, OntoNotes and MedMentions, emulating the difficulty of real-world zero-shot learning by testing models on the rarest entity classes. Our proposed approach outperforms baselines adapted from machine reading comprehension and zero-shot text classification. Furthermore, we assess the effect of different class descriptions for this task.</abstract>
    <identifier type="citekey">aly-etal-2021-leveraging</identifier>
    <identifier type="doi">10.18653/v1/2021.acl-long.120</identifier>
    <location>
        <url>https://aclanthology.org/2021.acl-long.120</url>
    </location>
    <part>
        <date>2021-aug</date>
        <extent unit="page">
            <start>1516</start>
            <end>1528</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification
%A Aly, Rami
%A Vlachos, Andreas
%A McDonald, Ryan
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 aug
%I Association for Computational Linguistics
%C Online
%F aly-etal-2021-leveraging
%X A common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for the target entity classes during training. Zero-shot learning approaches address this issue by learning models from classes with training data that can predict classes without it. This paper presents the first approach for zero-shot NERC, introducing novel architectures that leverage the fact that textual descriptions for many entity classes occur naturally. We address the zero-shot NERC specific challenge that the not-an-entity class is not well defined as different entity classes are considered in training and testing. For evaluation, we adapt two datasets, OntoNotes and MedMentions, emulating the difficulty of real-world zero-shot learning by testing models on the rarest entity classes. Our proposed approach outperforms baselines adapted from machine reading comprehension and zero-shot text classification. Furthermore, we assess the effect of different class descriptions for this task.
%R 10.18653/v1/2021.acl-long.120
%U https://aclanthology.org/2021.acl-long.120
%U https://doi.org/10.18653/v1/2021.acl-long.120
%P 1516-1528

Markdown (Informal)

[Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification](https://aclanthology.org/2021.acl-long.120) (Aly et al., ACL 2021)

• Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification (Aly et al., ACL 2021)

ACL

• Rami Aly, Andreas Vlachos, and Ryan McDonald. 2021. Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1516–1528, Online. Association for Computational Linguistics.