<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="noble-maraev-2021-large">
    <titleInfo>
        <title>Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bill</namePart>
        <namePart type="family">Noble</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vladislav</namePart>
        <namePart type="family">Maraev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 14th International Conference on Computational Semantics (IWCS)</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Groningen, The Netherlands (online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We use dialogue act recognition (DAR) to investigate how well BERT represents utterances in dialogue, and how fine-tuning and large-scale pre-training contribute to its performance. We find that while both the standard BERT pre-training and pretraining on dialogue-like data are useful, task-specific fine-tuning is essential for good performance.</abstract>
    <identifier type="citekey">noble-maraev-2021-large</identifier>
    <location>
        <url>https://aclanthology.org/2021.iwcs-1.16</url>
    </location>
    <part>
        <date>2021-06</date>
        <extent unit="page">
            <start>166</start>
            <end>172</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning
%A Noble, Bill
%A Maraev, Vladislav
%S Proceedings of the 14th International Conference on Computational Semantics (IWCS)
%D 2021
%8 June
%I Association for Computational Linguistics
%C Groningen, The Netherlands (online)
%F noble-maraev-2021-large
%X We use dialogue act recognition (DAR) to investigate how well BERT represents utterances in dialogue, and how fine-tuning and large-scale pre-training contribute to its performance. We find that while both the standard BERT pre-training and pretraining on dialogue-like data are useful, task-specific fine-tuning is essential for good performance.
%U https://aclanthology.org/2021.iwcs-1.16
%P 166-172

Markdown (Informal)

[Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning](https://aclanthology.org/2021.iwcs-1.16) (Noble & Maraev, IWCS 2021)

• Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning (Noble & Maraev, IWCS 2021)

ACL

• Bill Noble and Vladislav Maraev. 2021. Large-scale text pre-training helps with dialogue act recognition, but not without fine-tuning. In Proceedings of the 14th International Conference on Computational Semantics (IWCS), pages 166–172, Groningen, The Netherlands (online). Association for Computational Linguistics.