<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="micheli-etal-2020-importance">
    <titleInfo>
        <title>On the importance of pre-training data volume for compact language models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Vincent</namePart>
        <namePart type="family">Micheli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Martin</namePart>
        <namePart type="family">d’Hoffschmidt</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Fleuret</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent advances in language modeling have led to computationally intensive and resource-demanding state-of-the-art models. In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language models. Multiple BERT-based models are trained on gradually increasing amounts of French text. Through fine-tuning on the French Question Answering Dataset (FQuAD), we observe that well-performing models are obtained with as little as 100 MB of text. In addition, we show that past critically low amounts of pre-training data, an intermediate pre-training step on the task-specific corpus does not yield substantial improvements.</abstract>
    <identifier type="citekey">micheli-etal-2020-importance</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.632</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.632</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>7853</start>
            <end>7858</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the importance of pre-training data volume for compact language models
%A Micheli, Vincent
%A d’Hoffschmidt, Martin
%A Fleuret, François
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F micheli-etal-2020-importance
%X Recent advances in language modeling have led to computationally intensive and resource-demanding state-of-the-art models. In an effort towards sustainable practices, we study the impact of pre-training data volume on compact language models. Multiple BERT-based models are trained on gradually increasing amounts of French text. Through fine-tuning on the French Question Answering Dataset (FQuAD), we observe that well-performing models are obtained with as little as 100 MB of text. In addition, we show that past critically low amounts of pre-training data, an intermediate pre-training step on the task-specific corpus does not yield substantial improvements.
%R 10.18653/v1/2020.emnlp-main.632
%U https://aclanthology.org/2020.emnlp-main.632
%U https://doi.org/10.18653/v1/2020.emnlp-main.632
%P 7853-7858

Markdown (Informal)

[On the importance of pre-training data volume for compact language models](https://aclanthology.org/2020.emnlp-main.632) (Micheli et al., EMNLP 2020)

• On the importance of pre-training data volume for compact language models (Micheli et al., EMNLP 2020)

ACL

• Vincent Micheli, Martin d’Hoffschmidt, and François Fleuret. 2020. On the importance of pre-training data volume for compact language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7853–7858, Online. Association for Computational Linguistics.