<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vahtola-creutz-2024-toward">
    <titleInfo>
        <title>Toward the Modular Training of Controlled Paraphrase Adapters</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Teemu</namePart>
        <namePart type="family">Vahtola</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mathias</namePart>
        <namePart type="family">Creutz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Raúl</namePart>
            <namePart type="family">Vázquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Timothee</namePart>
            <namePart type="family">Mickus</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jörg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="family">Vulić</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ahmet</namePart>
            <namePart type="family">Üstün</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St Julians, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Controlled paraphrase generation often focuses on a specific aspect of paraphrasing, for instance syntactically controlled paraphrase generation. However, these models face a limitation: they lack modularity. Consequently adapting them for another aspect, such as lexical variation, needs full retraining of the model each time. To enhance the flexibility in training controlled paraphrase models, our proposition involves incrementally training a modularized system for controlled paraphrase generation for English. We start by fine-tuning a pretrained language model to learn the broad task of paraphrase generation, generally emphasizing meaning preservation and surface form variation. Subsequently, we train a specialized sub-task adapter with limited sub-task specific training data. We can then leverage this adapter in guiding the paraphrase generation process toward a desired output aligning with the distinctive features within the sub-task training data. The preliminary results on comparing the fine-tuned and adapted model against various competing systems indicates that the most successful method for mastering both general paraphrasing skills and task-specific expertise follows a two-stage approach. This approach involves starting with the initial fine-tuning of a generic paraphrase model and subsequently tailoring it for the specific sub-task.</abstract>
    <identifier type="citekey">vahtola-creutz-2024-toward</identifier>
    <location>
        <url>https://aclanthology.org/2024.moomin-1.1</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1</start>
            <end>6</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Toward the Modular Training of Controlled Paraphrase Adapters
%A Vahtola, Teemu
%A Creutz, Mathias
%Y Vázquez, Raúl
%Y Mickus, Timothee
%Y Tiedemann, Jörg
%Y Vulić, Ivan
%Y Üstün, Ahmet
%S Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St Julians, Malta
%F vahtola-creutz-2024-toward
%X Controlled paraphrase generation often focuses on a specific aspect of paraphrasing, for instance syntactically controlled paraphrase generation. However, these models face a limitation: they lack modularity. Consequently adapting them for another aspect, such as lexical variation, needs full retraining of the model each time. To enhance the flexibility in training controlled paraphrase models, our proposition involves incrementally training a modularized system for controlled paraphrase generation for English. We start by fine-tuning a pretrained language model to learn the broad task of paraphrase generation, generally emphasizing meaning preservation and surface form variation. Subsequently, we train a specialized sub-task adapter with limited sub-task specific training data. We can then leverage this adapter in guiding the paraphrase generation process toward a desired output aligning with the distinctive features within the sub-task training data. The preliminary results on comparing the fine-tuned and adapted model against various competing systems indicates that the most successful method for mastering both general paraphrasing skills and task-specific expertise follows a two-stage approach. This approach involves starting with the initial fine-tuning of a generic paraphrase model and subsequently tailoring it for the specific sub-task.
%U https://aclanthology.org/2024.moomin-1.1
%P 1-6

Markdown (Informal)

[Toward the Modular Training of Controlled Paraphrase Adapters](https://aclanthology.org/2024.moomin-1.1) (Vahtola & Creutz, MOOMIN-WS 2024)

• Toward the Modular Training of Controlled Paraphrase Adapters (Vahtola & Creutz, MOOMIN-WS 2024)

ACL

• Teemu Vahtola and Mathias Creutz. 2024. Toward the Modular Training of Controlled Paraphrase Adapters. In Proceedings of the 1st Workshop on Modular and Open Multilingual NLP (MOOMIN 2024), pages 1–6, St Julians, Malta. Association for Computational Linguistics.