@inproceedings{cruz-cheng-2022-improving,
title = "Improving Large-scale Language Models and Resources for {F}ilipino",
author = "Cruz, Jan Christian Blaise and
Cheng, Charibeth",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.703/",
pages = "6548--6555",
abstract = "In this paper, we improve on existing language resources for the low-resource Filipino language in two ways. First, we outline the construction of the TLUnified dataset, a large-scale pretraining corpus that serves as an improvement over smaller existing pretraining datasets for the language in terms of scale and topic variety. Second, we pretrain new Transformer language models following the RoBERTa pretraining technique to supplant existing models trained with small corpora. Our new RoBERTa models show significant improvements over existing Filipino models in three benchmark datasets with an average gain of 4.47{\%} test accuracy across three classification tasks with varying difficulty."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cruz-cheng-2022-improving">
<titleInfo>
<title>Improving Large-scale Language Models and Resources for Filipino</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Christian</namePart>
<namePart type="given">Blaise</namePart>
<namePart type="family">Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charibeth</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we improve on existing language resources for the low-resource Filipino language in two ways. First, we outline the construction of the TLUnified dataset, a large-scale pretraining corpus that serves as an improvement over smaller existing pretraining datasets for the language in terms of scale and topic variety. Second, we pretrain new Transformer language models following the RoBERTa pretraining technique to supplant existing models trained with small corpora. Our new RoBERTa models show significant improvements over existing Filipino models in three benchmark datasets with an average gain of 4.47% test accuracy across three classification tasks with varying difficulty.</abstract>
<identifier type="citekey">cruz-cheng-2022-improving</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.703/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6548</start>
<end>6555</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Large-scale Language Models and Resources for Filipino
%A Cruz, Jan Christian Blaise
%A Cheng, Charibeth
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F cruz-cheng-2022-improving
%X In this paper, we improve on existing language resources for the low-resource Filipino language in two ways. First, we outline the construction of the TLUnified dataset, a large-scale pretraining corpus that serves as an improvement over smaller existing pretraining datasets for the language in terms of scale and topic variety. Second, we pretrain new Transformer language models following the RoBERTa pretraining technique to supplant existing models trained with small corpora. Our new RoBERTa models show significant improvements over existing Filipino models in three benchmark datasets with an average gain of 4.47% test accuracy across three classification tasks with varying difficulty.
%U https://aclanthology.org/2022.lrec-1.703/
%P 6548-6555
Markdown (Informal)
[Improving Large-scale Language Models and Resources for Filipino](https://aclanthology.org/2022.lrec-1.703/) (Cruz & Cheng, LREC 2022)
ACL