@inproceedings{imperial-kochmar-2023-basahacorpus,
title = "{B}asaha{C}orpus: An Expanded Linguistic Resource for Readability Assessment in {C}entral {P}hilippine Languages",
author = "Imperial, Joseph Marvin and
Kochmar, Ekaterina",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.388",
doi = "10.18653/v1/2023.emnlp-main.388",
pages = "6302--6309",
abstract = "Current research on automatic readability assessment (ARA) has focused on improving the performance of models in high-resource languages such as English. In this work, we introduce and release BasahaCorpus as part of an initiative aimed at expanding available corpora and baseline models for readability assessment in lower resource languages in the Philippines. We compiled a corpus of short fictional narratives written in Hiligaynon, Minasbate, Karay-a, and Rinconada{---}languages belonging to the Central Philippine family tree subgroup{---}to train ARA models using surface-level, syllable-pattern, and n-gram overlap features. We also propose a new hierarchical cross-lingual modeling approach that takes advantage of a language{'}s placement in the family tree to increase the amount of available training data. Our study yields encouraging results that support previous work showcasing the efficacy of cross-lingual models in low-resource settings, as well as similarities in highly informative linguistic features for mutually intelligible languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imperial-kochmar-2023-basahacorpus">
<titleInfo>
<title>BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">Marvin</namePart>
<namePart type="family">Imperial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current research on automatic readability assessment (ARA) has focused on improving the performance of models in high-resource languages such as English. In this work, we introduce and release BasahaCorpus as part of an initiative aimed at expanding available corpora and baseline models for readability assessment in lower resource languages in the Philippines. We compiled a corpus of short fictional narratives written in Hiligaynon, Minasbate, Karay-a, and Rinconada—languages belonging to the Central Philippine family tree subgroup—to train ARA models using surface-level, syllable-pattern, and n-gram overlap features. We also propose a new hierarchical cross-lingual modeling approach that takes advantage of a language’s placement in the family tree to increase the amount of available training data. Our study yields encouraging results that support previous work showcasing the efficacy of cross-lingual models in low-resource settings, as well as similarities in highly informative linguistic features for mutually intelligible languages.</abstract>
<identifier type="citekey">imperial-kochmar-2023-basahacorpus</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.388</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.388</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6302</start>
<end>6309</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages
%A Imperial, Joseph Marvin
%A Kochmar, Ekaterina
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F imperial-kochmar-2023-basahacorpus
%X Current research on automatic readability assessment (ARA) has focused on improving the performance of models in high-resource languages such as English. In this work, we introduce and release BasahaCorpus as part of an initiative aimed at expanding available corpora and baseline models for readability assessment in lower resource languages in the Philippines. We compiled a corpus of short fictional narratives written in Hiligaynon, Minasbate, Karay-a, and Rinconada—languages belonging to the Central Philippine family tree subgroup—to train ARA models using surface-level, syllable-pattern, and n-gram overlap features. We also propose a new hierarchical cross-lingual modeling approach that takes advantage of a language’s placement in the family tree to increase the amount of available training data. Our study yields encouraging results that support previous work showcasing the efficacy of cross-lingual models in low-resource settings, as well as similarities in highly informative linguistic features for mutually intelligible languages.
%R 10.18653/v1/2023.emnlp-main.388
%U https://aclanthology.org/2023.emnlp-main.388
%U https://doi.org/10.18653/v1/2023.emnlp-main.388
%P 6302-6309
Markdown (Informal)
[BasahaCorpus: An Expanded Linguistic Resource for Readability Assessment in Central Philippine Languages](https://aclanthology.org/2023.emnlp-main.388) (Imperial & Kochmar, EMNLP 2023)
ACL