<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duval-etal-2021-breaking">
    <titleInfo>
        <title>Breaking Writer’s Block: Low-cost Fine-tuning of Natural Language Generation Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Alexandre</namePart>
        <namePart type="family">Duval</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Lamson</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gaël</namePart>
        <namePart type="family">de Léséleuc de Kérouara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthias</namePart>
        <namePart type="family">Gallé</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Dimitra</namePart>
            <namePart type="family">Gkatzia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Djamé</namePart>
            <namePart type="family">Seddah</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>It is standard procedure these days to solve Information Extraction task by fine-tuning large pre-trained language models. This is not the case for generation task, which relies on a variety of techniques for controlled language generation. In this paper, we describe a system that fine-tunes a natural language generation model for the problem of solving writer’s block. The fine-tuning changes the conditioning to also include the right context in addition to the left context, as well as an optional list of entities, the size, the genre and a summary of the paragraph that the human author wishes to generate. Our proposed fine-tuning obtains excellent results, even with a small number of epochs and a total cost of USD 150. The system can be accessed as a web-service and all the code is released. A video showcasing the interface and the model is also available.</abstract>
    <identifier type="citekey">duval-etal-2021-breaking</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-demos.33</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-demos.33</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>278</start>
            <end>287</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Breaking Writer’s Block: Low-cost Fine-tuning of Natural Language Generation Models
%A Duval, Alexandre
%A Lamson, Thomas
%A de Léséleuc de Kérouara, Gaël
%A Gallé, Matthias
%Y Gkatzia, Dimitra
%Y Seddah, Djamé
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F duval-etal-2021-breaking
%X It is standard procedure these days to solve Information Extraction task by fine-tuning large pre-trained language models. This is not the case for generation task, which relies on a variety of techniques for controlled language generation. In this paper, we describe a system that fine-tunes a natural language generation model for the problem of solving writer’s block. The fine-tuning changes the conditioning to also include the right context in addition to the left context, as well as an optional list of entities, the size, the genre and a summary of the paragraph that the human author wishes to generate. Our proposed fine-tuning obtains excellent results, even with a small number of epochs and a total cost of USD 150. The system can be accessed as a web-service and all the code is released. A video showcasing the interface and the model is also available.
%R 10.18653/v1/2021.eacl-demos.33
%U https://aclanthology.org/2021.eacl-demos.33
%U https://doi.org/10.18653/v1/2021.eacl-demos.33
%P 278-287

Markdown (Informal)

[Breaking Writer’s Block: Low-cost Fine-tuning of Natural Language Generation Models](https://aclanthology.org/2021.eacl-demos.33) (Duval et al., EACL 2021)

• Breaking Writer’s Block: Low-cost Fine-tuning of Natural Language Generation Models (Duval et al., EACL 2021)

ACL

• Alexandre Duval, Thomas Lamson, Gaël de Léséleuc de Kérouara, and Matthias Gallé. 2021. Breaking Writer’s Block: Low-cost Fine-tuning of Natural Language Generation Models. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 278–287, Online. Association for Computational Linguistics.