<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mtumbuka-schockaert-2024-encore">
    <titleInfo>
        <title>EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Frank</namePart>
        <namePart type="family">Mtumbuka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Steven</namePart>
        <namePart type="family">Schockaert</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Entity typing is the task of assigning semantic types to the entities that are mentioned in a text. In the case of fine-grained entity typing (FET), a large set of candidate type labels is considered. Since obtaining sufficient amounts of manual annotations is then prohibitively expensive, FET models are typically trained using distant supervision. In this paper, we propose to improve on this process by pre-training an entity encoder such that embeddings of coreferring entities are more similar to each other than to the embeddings of other entities. The main problem with this strategy, which helps to explain why it has not previously been considered, is that predicted coreference links are often too noisy. We show that this problem can be addressed by using a simple trick: we only consider coreference links that are predicted by two different off-the-shelf systems. With this prudent use of coreference links, our pre-training strategy allows us to improve the state-of-the-art in benchmarks on fine-grained entity typing, as well as traditional entity extraction.</abstract>
    <identifier type="citekey">mtumbuka-schockaert-2024-encore</identifier>
    <location>
        <url>https://aclanthology.org/2024.eacl-long.106</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1768</start>
            <end>1781</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains
%A Mtumbuka, Frank
%A Schockaert, Steven
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F mtumbuka-schockaert-2024-encore
%X Entity typing is the task of assigning semantic types to the entities that are mentioned in a text. In the case of fine-grained entity typing (FET), a large set of candidate type labels is considered. Since obtaining sufficient amounts of manual annotations is then prohibitively expensive, FET models are typically trained using distant supervision. In this paper, we propose to improve on this process by pre-training an entity encoder such that embeddings of coreferring entities are more similar to each other than to the embeddings of other entities. The main problem with this strategy, which helps to explain why it has not previously been considered, is that predicted coreference links are often too noisy. We show that this problem can be addressed by using a simple trick: we only consider coreference links that are predicted by two different off-the-shelf systems. With this prudent use of coreference links, our pre-training strategy allows us to improve the state-of-the-art in benchmarks on fine-grained entity typing, as well as traditional entity extraction.
%U https://aclanthology.org/2024.eacl-long.106
%P 1768-1781

Markdown (Informal)

[EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains](https://aclanthology.org/2024.eacl-long.106) (Mtumbuka & Schockaert, EACL 2024)

• EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains (Mtumbuka & Schockaert, EACL 2024)

ACL

• Frank Mtumbuka and Steven Schockaert. 2024. EnCore: Fine-Grained Entity Typing by Pre-Training Entity Encoders on Coreference Chains. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1768–1781, St. Julian’s, Malta. Association for Computational Linguistics.