<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="asada-miwa-2025-addressing">
    <titleInfo>
        <title>Addressing the Training-Inference Discrepancy in Discrete Diffusion for Text Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Masaki</namePart>
        <namePart type="family">Asada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Makoto</namePart>
        <namePart type="family">Miwa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 31st International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Owen</namePart>
            <namePart type="family">Rambow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leo</namePart>
            <namePart type="family">Wanner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hend</namePart>
            <namePart type="family">Al-Khalifa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barbara</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Eugenio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Schockaert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This study addresses the discrepancy between training and inference in discrete diffusion models for text generation. We propose two novel strategies: (1) a training schema that considers two-step diffusion processes, allowing the model to use its own predicted output as input for subsequent steps during training and (2) a scheduling technique that gradually increases the probability of using self-generated text as training progresses. Experiments conducted on four widely used text generation benchmark datasets demonstrate that both proposed strategies improve the performance of discrete diffusion models in text generation.</abstract>
    <identifier type="citekey">asada-miwa-2025-addressing</identifier>
    <location>
        <url>https://aclanthology.org/2025.coling-main.477/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>7156</start>
            <end>7164</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Addressing the Training-Inference Discrepancy in Discrete Diffusion for Text Generation
%A Asada, Masaki
%A Miwa, Makoto
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F asada-miwa-2025-addressing
%X This study addresses the discrepancy between training and inference in discrete diffusion models for text generation. We propose two novel strategies: (1) a training schema that considers two-step diffusion processes, allowing the model to use its own predicted output as input for subsequent steps during training and (2) a scheduling technique that gradually increases the probability of using self-generated text as training progresses. Experiments conducted on four widely used text generation benchmark datasets demonstrate that both proposed strategies improve the performance of discrete diffusion models in text generation.
%U https://aclanthology.org/2025.coling-main.477/
%P 7156-7164

Markdown (Informal)

[Addressing the Training-Inference Discrepancy in Discrete Diffusion for Text Generation](https://aclanthology.org/2025.coling-main.477/) (Asada & Miwa, COLING 2025)

• Addressing the Training-Inference Discrepancy in Discrete Diffusion for Text Generation (Asada & Miwa, COLING 2025)

ACL

• Masaki Asada and Makoto Miwa. 2025. Addressing the Training-Inference Discrepancy in Discrete Diffusion for Text Generation. In Proceedings of the 31st International Conference on Computational Linguistics, pages 7156–7164, Abu Dhabi, UAE. Association for Computational Linguistics.