<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="edman-etal-2022-subword">
    <titleInfo>
        <title>Subword-Delimited Downsampling for Better Character-Level Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lukas</namePart>
        <namePart type="family">Edman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antonio</namePart>
        <namePart type="family">Toral</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gertjan</namePart>
        <namePart type="family">van Noord</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</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">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better models. Recent works have shown character-level models to be competitive with subword models, but costly in terms of time and computation. Character-level models with a downsampling component alleviate this, but at the cost of quality, particularly for machine translation. This work analyzes the problems of previous downsampling methods and introduces a novel downsampling method which is informed by subwords.This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.</abstract>
    <identifier type="citekey">edman-etal-2022-subword</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-emnlp.69</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-emnlp.69</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>981</start>
            <end>992</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Subword-Delimited Downsampling for Better Character-Level Translation
%A Edman, Lukas
%A Toral, Antonio
%A van Noord, Gertjan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F edman-etal-2022-subword
%X Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better models. Recent works have shown character-level models to be competitive with subword models, but costly in terms of time and computation. Character-level models with a downsampling component alleviate this, but at the cost of quality, particularly for machine translation. This work analyzes the problems of previous downsampling methods and introduces a novel downsampling method which is informed by subwords.This new downsampling method not only outperforms existing downsampling methods, showing that downsampling characters can be done without sacrificing quality, but also leads to promising performance compared to subword models for translation.
%R 10.18653/v1/2022.findings-emnlp.69
%U https://aclanthology.org/2022.findings-emnlp.69
%U https://doi.org/10.18653/v1/2022.findings-emnlp.69
%P 981-992

Markdown (Informal)

[Subword-Delimited Downsampling for Better Character-Level Translation](https://aclanthology.org/2022.findings-emnlp.69) (Edman et al., Findings 2022)

• Subword-Delimited Downsampling for Better Character-Level Translation (Edman et al., Findings 2022)

ACL

• Lukas Edman, Antonio Toral, and Gertjan van Noord. 2022. Subword-Delimited Downsampling for Better Character-Level Translation. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 981–992, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.