@inproceedings{lee-etal-2024-scriptmix,
title = "{S}cript{M}ix: Mixing Scripts for Low-resource Language Parsing",
author = "Lee, Jaeseong and
Lee, Dohyeon and
Hwang, Seung-won",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.357",
pages = "6430--6444",
abstract = "Despite the success of multilingual pretrained language models (mPLMs) for tasks such as dependency parsing (DEP) or part-of-speech (POS) tagging, their coverage of 100s of languages is still limited, as most of the 6500+ languages remains {``}unseen{''}. To adapt mPLMs for including such unseen langs, existing work has considered transliteration and vocabulary augmentation. Meanwhile, the consideration of combining the two has been surprisingly lacking. To understand why, we identify both complementary strengths of the two, and the hurdles to realizing it. Based on this observation, we propose ScriptMix, combining two strengths, and overcoming the hurdle.Specifically, ScriptMix a) is trained with dual-script corpus to combine strengths, but b) with separate modules to avoid gradient conflict. In combining modules properly, we also point out the limitation of the conventional method AdapterFusion, and propose AdapterFusion+ to overcome it. We empirically show ScriptMix is effective{--} ScriptMix improves the POS accuracy by up to 14{\%}, and improves the DEP LAS score by up to 5.6{\%}. Our code is publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2024-scriptmix">
<titleInfo>
<title>ScriptMix: Mixing Scripts for Low-resource Language Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jaeseong</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dohyeon</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the success of multilingual pretrained language models (mPLMs) for tasks such as dependency parsing (DEP) or part-of-speech (POS) tagging, their coverage of 100s of languages is still limited, as most of the 6500+ languages remains “unseen”. To adapt mPLMs for including such unseen langs, existing work has considered transliteration and vocabulary augmentation. Meanwhile, the consideration of combining the two has been surprisingly lacking. To understand why, we identify both complementary strengths of the two, and the hurdles to realizing it. Based on this observation, we propose ScriptMix, combining two strengths, and overcoming the hurdle.Specifically, ScriptMix a) is trained with dual-script corpus to combine strengths, but b) with separate modules to avoid gradient conflict. In combining modules properly, we also point out the limitation of the conventional method AdapterFusion, and propose AdapterFusion+ to overcome it. We empirically show ScriptMix is effective– ScriptMix improves the POS accuracy by up to 14%, and improves the DEP LAS score by up to 5.6%. Our code is publicly available.</abstract>
<identifier type="citekey">lee-etal-2024-scriptmix</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.357</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>6430</start>
<end>6444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ScriptMix: Mixing Scripts for Low-resource Language Parsing
%A Lee, Jaeseong
%A Lee, Dohyeon
%A Hwang, Seung-won
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F lee-etal-2024-scriptmix
%X Despite the success of multilingual pretrained language models (mPLMs) for tasks such as dependency parsing (DEP) or part-of-speech (POS) tagging, their coverage of 100s of languages is still limited, as most of the 6500+ languages remains “unseen”. To adapt mPLMs for including such unseen langs, existing work has considered transliteration and vocabulary augmentation. Meanwhile, the consideration of combining the two has been surprisingly lacking. To understand why, we identify both complementary strengths of the two, and the hurdles to realizing it. Based on this observation, we propose ScriptMix, combining two strengths, and overcoming the hurdle.Specifically, ScriptMix a) is trained with dual-script corpus to combine strengths, but b) with separate modules to avoid gradient conflict. In combining modules properly, we also point out the limitation of the conventional method AdapterFusion, and propose AdapterFusion+ to overcome it. We empirically show ScriptMix is effective– ScriptMix improves the POS accuracy by up to 14%, and improves the DEP LAS score by up to 5.6%. Our code is publicly available.
%U https://aclanthology.org/2024.naacl-long.357
%P 6430-6444
Markdown (Informal)
[ScriptMix: Mixing Scripts for Low-resource Language Parsing](https://aclanthology.org/2024.naacl-long.357) (Lee et al., NAACL 2024)
ACL
- Jaeseong Lee, Dohyeon Lee, and Seung-won Hwang. 2024. ScriptMix: Mixing Scripts for Low-resource Language Parsing. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6430–6444, Mexico City, Mexico. Association for Computational Linguistics.