<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="berezin-batura-2022-named">
    <titleInfo>
        <title>Named Entity Inclusion in Abstractive Text Summarization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sergey</namePart>
        <namePart type="family">Berezin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatiana</namePart>
        <namePart type="family">Batura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on Scholarly Document Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We address the named entity omission - the drawback of many current abstractive text summarizers. We suggest a custom pretraining objective to enhance the model’s attention on the named entities in a text. At first, the named entity recognition model RoBERTa is trained to determine named entities in the text. After that this model is used to mask named entities in the text and the BART model is trained to reconstruct them. Next, BART model is fine-tuned on the summarization task. Our experiments showed that this pretraining approach drastically improves named entity inclusion precision and recall metrics.</abstract>
    <identifier type="citekey">berezin-batura-2022-named</identifier>
    <location>
        <url>https://aclanthology.org/2022.sdp-1.17</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>158</start>
            <end>162</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Named Entity Inclusion in Abstractive Text Summarization
%A Berezin, Sergey
%A Batura, Tatiana
%S Proceedings of the Third Workshop on Scholarly Document Processing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F berezin-batura-2022-named
%X We address the named entity omission - the drawback of many current abstractive text summarizers. We suggest a custom pretraining objective to enhance the model’s attention on the named entities in a text. At first, the named entity recognition model RoBERTa is trained to determine named entities in the text. After that this model is used to mask named entities in the text and the BART model is trained to reconstruct them. Next, BART model is fine-tuned on the summarization task. Our experiments showed that this pretraining approach drastically improves named entity inclusion precision and recall metrics.
%U https://aclanthology.org/2022.sdp-1.17
%P 158-162

Markdown (Informal)

[Named Entity Inclusion in Abstractive Text Summarization](https://aclanthology.org/2022.sdp-1.17) (Berezin & Batura, sdp 2022)

• Named Entity Inclusion in Abstractive Text Summarization (Berezin & Batura, sdp 2022)

ACL

• Sergey Berezin and Tatiana Batura. 2022. Named Entity Inclusion in Abstractive Text Summarization. In Proceedings of the Third Workshop on Scholarly Document Processing, pages 158–162, Gyeongju, Republic of Korea. Association for Computational Linguistics.