<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demirag-etal-2024-benchmarking">
    <titleInfo>
        <title>Benchmarking Diffusion Models for Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yunus</namePart>
        <namePart type="family">Demirag</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danni</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="family">Niehues</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 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Neele</namePart>
            <namePart type="family">Falk</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Papi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mike</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Diffusion models have recently shown great potential on many generative tasks.In this work, we explore diffusion models for machine translation (MT).We adapt two prominent diffusion-based text generation models, Diffusion-LM and DiffuSeq, to perform machine translation.As the diffusion models generate non-autoregressively (NAR),we draw parallels to NAR machine translation models.With a comparison to conventional Transformer-based translation models, as well as to the Levenshtein Transformer,an established NAR MT model,we show that the multimodality problem that limits NAR machine translation performance is also a challenge to diffusion models.We demonstrate that knowledge distillation from an autoregressive model improves the performance of diffusion-based MT.A thorough analysis on the translation quality of inputs of different lengths shows that the diffusion models struggle more on long-range dependencies than other models.</abstract>
    <identifier type="citekey">demirag-etal-2024-benchmarking</identifier>
    <location>
        <url>https://aclanthology.org/2024.eacl-srw.25</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>313</start>
            <end>324</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Benchmarking Diffusion Models for Machine Translation
%A Demirag, Yunus
%A Liu, Danni
%A Niehues, Jan
%Y Falk, Neele
%Y Papi, Sara
%Y Zhang, Mike
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F demirag-etal-2024-benchmarking
%X Diffusion models have recently shown great potential on many generative tasks.In this work, we explore diffusion models for machine translation (MT).We adapt two prominent diffusion-based text generation models, Diffusion-LM and DiffuSeq, to perform machine translation.As the diffusion models generate non-autoregressively (NAR),we draw parallels to NAR machine translation models.With a comparison to conventional Transformer-based translation models, as well as to the Levenshtein Transformer,an established NAR MT model,we show that the multimodality problem that limits NAR machine translation performance is also a challenge to diffusion models.We demonstrate that knowledge distillation from an autoregressive model improves the performance of diffusion-based MT.A thorough analysis on the translation quality of inputs of different lengths shows that the diffusion models struggle more on long-range dependencies than other models.
%U https://aclanthology.org/2024.eacl-srw.25
%P 313-324

Markdown (Informal)

[Benchmarking Diffusion Models for Machine Translation](https://aclanthology.org/2024.eacl-srw.25) (Demirag et al., EACL 2024)

• Benchmarking Diffusion Models for Machine Translation (Demirag et al., EACL 2024)

ACL

• Yunus Demirag, Danni Liu, and Jan Niehues. 2024. Benchmarking Diffusion Models for Machine Translation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 313–324, St. Julian’s, Malta. Association for Computational Linguistics.