@inproceedings{limisiewicz-etal-2024-myte,
title = "{MYTE}: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling",
author = "Limisiewicz, Tomasz and
Blevins, Terra and
Gonen, Hila and
Ahia, Orevaoghene and
Zettlemoyer, Luke",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.804",
pages = "15059--15076",
abstract = "A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts.Although contemporary text encoding methods cover most of the world{'}s writing systems, they exhibit bias towards the high-resource languages of the Global West. As a result, texts of underrepresented languages tend to be segmented into long sequences of linguistically meaningless units. To address the disparities, we introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. Our encoding convention (MYTE) is based on morphemes, as their inventories are more balanced across languages than characters, which are used in previous methods. We show that MYTE produces shorter encodings for all 99 analyzed languages, with the most notable improvements for non-European languages and non-Latin scripts. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="limisiewicz-etal-2024-myte">
<titleInfo>
<title>MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Limisiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terra</namePart>
<namePart type="family">Blevins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hila</namePart>
<namePart type="family">Gonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orevaoghene</namePart>
<namePart type="family">Ahia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts.Although contemporary text encoding methods cover most of the world’s writing systems, they exhibit bias towards the high-resource languages of the Global West. As a result, texts of underrepresented languages tend to be segmented into long sequences of linguistically meaningless units. To address the disparities, we introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. Our encoding convention (MYTE) is based on morphemes, as their inventories are more balanced across languages than characters, which are used in previous methods. We show that MYTE produces shorter encodings for all 99 analyzed languages, with the most notable improvements for non-European languages and non-Latin scripts. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.</abstract>
<identifier type="citekey">limisiewicz-etal-2024-myte</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.804</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>15059</start>
<end>15076</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling
%A Limisiewicz, Tomasz
%A Blevins, Terra
%A Gonen, Hila
%A Ahia, Orevaoghene
%A Zettlemoyer, Luke
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F limisiewicz-etal-2024-myte
%X A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts.Although contemporary text encoding methods cover most of the world’s writing systems, they exhibit bias towards the high-resource languages of the Global West. As a result, texts of underrepresented languages tend to be segmented into long sequences of linguistically meaningless units. To address the disparities, we introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. Our encoding convention (MYTE) is based on morphemes, as their inventories are more balanced across languages than characters, which are used in previous methods. We show that MYTE produces shorter encodings for all 99 analyzed languages, with the most notable improvements for non-European languages and non-Latin scripts. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.
%U https://aclanthology.org/2024.acl-long.804
%P 15059-15076
Markdown (Informal)
[MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling](https://aclanthology.org/2024.acl-long.804) (Limisiewicz et al., ACL 2024)
ACL