@inproceedings{layacan-etal-2024-zero,
title = "Zero-shot Cross-lingual {POS} Tagging for {F}ilipino",
author = "Layacan, Jimson and
Flores, Isaiah Edri W. and
Tan, Katrina and
Estuar, Ma. Regina E. and
Montalan, Jann and
De Leon, Marlene M.",
editor = "Serikov, Oleg and
Voloshina, Ekaterina and
Postnikova, Anna and
Muradoglu, Saliha and
Le Ferrand, Eric and
Klyachko, Elena and
Vylomova, Ekaterina and
Shavrina, Tatiana and
Tyers, Francis",
booktitle = "Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.fieldmatters-1.9/",
doi = "10.18653/v1/2024.fieldmatters-1.9",
pages = "69--77",
abstract = "Supervised learning approaches in NLP, exemplified by POS tagging, rely heavily on the presence of large amounts of annotated data. However, acquiring such data often requires significant amount of resources and incurs high costs. In this work, we explore zero-shot cross-lingual transfer learning to address data scarcity issues in Filipino POS tagging, particularly focusing on optimizing source language selection. Our zero-shot approach demonstrates superior performance compared to previous studies, with top-performing fine-tuned PLMs achieving F1 scores as high as 79.10{\%}. The analysis reveals moderate correlations between cross-lingual transfer performance and specific linguistic distances{--}featural, inventory, and syntactic{--}suggesting that source languages with these features closer to Filipino provide better results. We identify tokenizer optimization as a key challenge, as PLM tokenization sometimes fails to align with meaningful representations, thus hindering POS tagging performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="layacan-etal-2024-zero">
<titleInfo>
<title>Zero-shot Cross-lingual POS Tagging for Filipino</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimson</namePart>
<namePart type="family">Layacan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaiah</namePart>
<namePart type="given">Edri</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Flores</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrina</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ma.</namePart>
<namePart type="given">Regina</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Estuar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jann</namePart>
<namePart type="family">Montalan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marlene</namePart>
<namePart type="given">M</namePart>
<namePart type="family">De Leon</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 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Voloshina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Postnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Le Ferrand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Klyachko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatiana</namePart>
<namePart type="family">Shavrina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</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>Supervised learning approaches in NLP, exemplified by POS tagging, rely heavily on the presence of large amounts of annotated data. However, acquiring such data often requires significant amount of resources and incurs high costs. In this work, we explore zero-shot cross-lingual transfer learning to address data scarcity issues in Filipino POS tagging, particularly focusing on optimizing source language selection. Our zero-shot approach demonstrates superior performance compared to previous studies, with top-performing fine-tuned PLMs achieving F1 scores as high as 79.10%. The analysis reveals moderate correlations between cross-lingual transfer performance and specific linguistic distances–featural, inventory, and syntactic–suggesting that source languages with these features closer to Filipino provide better results. We identify tokenizer optimization as a key challenge, as PLM tokenization sometimes fails to align with meaningful representations, thus hindering POS tagging performance.</abstract>
<identifier type="citekey">layacan-etal-2024-zero</identifier>
<identifier type="doi">10.18653/v1/2024.fieldmatters-1.9</identifier>
<location>
<url>https://aclanthology.org/2024.fieldmatters-1.9/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>69</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot Cross-lingual POS Tagging for Filipino
%A Layacan, Jimson
%A Flores, Isaiah Edri W.
%A Tan, Katrina
%A Estuar, Ma. Regina E.
%A Montalan, Jann
%A De Leon, Marlene M.
%Y Serikov, Oleg
%Y Voloshina, Ekaterina
%Y Postnikova, Anna
%Y Muradoglu, Saliha
%Y Le Ferrand, Eric
%Y Klyachko, Elena
%Y Vylomova, Ekaterina
%Y Shavrina, Tatiana
%Y Tyers, Francis
%S Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F layacan-etal-2024-zero
%X Supervised learning approaches in NLP, exemplified by POS tagging, rely heavily on the presence of large amounts of annotated data. However, acquiring such data often requires significant amount of resources and incurs high costs. In this work, we explore zero-shot cross-lingual transfer learning to address data scarcity issues in Filipino POS tagging, particularly focusing on optimizing source language selection. Our zero-shot approach demonstrates superior performance compared to previous studies, with top-performing fine-tuned PLMs achieving F1 scores as high as 79.10%. The analysis reveals moderate correlations between cross-lingual transfer performance and specific linguistic distances–featural, inventory, and syntactic–suggesting that source languages with these features closer to Filipino provide better results. We identify tokenizer optimization as a key challenge, as PLM tokenization sometimes fails to align with meaningful representations, thus hindering POS tagging performance.
%R 10.18653/v1/2024.fieldmatters-1.9
%U https://aclanthology.org/2024.fieldmatters-1.9/
%U https://doi.org/10.18653/v1/2024.fieldmatters-1.9
%P 69-77
Markdown (Informal)
[Zero-shot Cross-lingual POS Tagging for Filipino](https://aclanthology.org/2024.fieldmatters-1.9/) (Layacan et al., FieldMatters 2024)
ACL
- Jimson Layacan, Isaiah Edri W. Flores, Katrina Tan, Ma. Regina E. Estuar, Jann Montalan, and Marlene M. De Leon. 2024. Zero-shot Cross-lingual POS Tagging for Filipino. In Proceedings of the 3rd Workshop on NLP Applications to Field Linguistics (Field Matters 2024), pages 69–77, Bangkok, Thailand. Association for Computational Linguistics.