<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2021-study">
    <titleInfo>
        <title>A Study on Contextualized Language Modeling for Machine Reading Comprehension</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chin-Ying</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yung-Chang</namePart>
        <namePart type="family">Hsu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Berlin</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)</title>
        </titleInfo>
        <originInfo>
            <publisher>The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)</publisher>
            <place>
                <placeTerm type="text">Taoyuan, Taiwan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>With the recent breakthrough of deep learning technologies, research on machine reading comprehension (MRC) has attracted much attention and found its versatile applications in many use cases. MRC is an important natural language processing (NLP) task aiming to assess the ability of a machine to understand natural language expressions, which is typically operationalized by first asking questions based on a given text paragraph and then receiving machine-generated answers in accordance with the given context paragraph and questions. In this paper, we leverage two novel pretrained language models built on top of Bidirectional Encoder Representations from Transformers (BERT), namely BERT-wwm and MacBERT, to develop effective MRC methods. In addition, we also seek to investigate whether additional incorporation of the categorical information about a context paragraph can benefit MRC or not, which is achieved based on performing context paragraph clustering on the training dataset. On the other hand, an ensemble learning approach is proposed to harness the synergistic power of the aforementioned two BERT-based models so as to further promote MRC performance.</abstract>
    <identifier type="citekey">wu-etal-2021-study</identifier>
    <location>
        <url>https://aclanthology.org/2021.rocling-1.7</url>
    </location>
    <part>
        <date>2021-10</date>
        <extent unit="page">
            <start>48</start>
            <end>57</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Study on Contextualized Language Modeling for Machine Reading Comprehension
%A Wu, Chin-Ying
%A Hsu, Yung-Chang
%A Chen, Berlin
%S Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021)
%D 2021
%8 October
%I The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)
%C Taoyuan, Taiwan
%F wu-etal-2021-study
%X With the recent breakthrough of deep learning technologies, research on machine reading comprehension (MRC) has attracted much attention and found its versatile applications in many use cases. MRC is an important natural language processing (NLP) task aiming to assess the ability of a machine to understand natural language expressions, which is typically operationalized by first asking questions based on a given text paragraph and then receiving machine-generated answers in accordance with the given context paragraph and questions. In this paper, we leverage two novel pretrained language models built on top of Bidirectional Encoder Representations from Transformers (BERT), namely BERT-wwm and MacBERT, to develop effective MRC methods. In addition, we also seek to investigate whether additional incorporation of the categorical information about a context paragraph can benefit MRC or not, which is achieved based on performing context paragraph clustering on the training dataset. On the other hand, an ensemble learning approach is proposed to harness the synergistic power of the aforementioned two BERT-based models so as to further promote MRC performance.
%U https://aclanthology.org/2021.rocling-1.7
%P 48-57

Markdown (Informal)

[A Study on Contextualized Language Modeling for Machine Reading Comprehension](https://aclanthology.org/2021.rocling-1.7) (Wu et al., ROCLING 2021)

• A Study on Contextualized Language Modeling for Machine Reading Comprehension (Wu et al., ROCLING 2021)

ACL

• Chin-Ying Wu, Yung-Chang Hsu, and Berlin Chen. 2021. A Study on Contextualized Language Modeling for Machine Reading Comprehension. In Proceedings of the 33rd Conference on Computational Linguistics and Speech Processing (ROCLING 2021), pages 48–57, Taoyuan, Taiwan. The Association for Computational Linguistics and Chinese Language Processing (ACLCLP).