@inproceedings{sung-shin-2023-diversifying,
title = "Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language {K}orean",
author = "Sung, Hakyung and
Shin, Gyu-Ho",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.767/",
doi = "10.18653/v1/2023.findings-emnlp.767",
pages = "11461--11473",
abstract = "This study investigates the extent to which currently available morpheme parsers/taggers apply to lesser-studied languages and language-usage contexts, with a focus on second language (L2) Korean. We pursue this inquiry by (1) training a neural-network model (pre-trained on first language [L1] Korean data) on varying L2 datasets and (2) measuring its morpheme parsing/POS tagging performance on L2 test sets from both the same and different sources of the L2 train sets. Results show that the L2 trained models generally excel in domain-specific tokenization and POS tagging compared to the L1 pre-trained baseline model. Interestingly, increasing the size of the L2 training data does not lead to improving model performance consistently."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sung-shin-2023-diversifying">
<titleInfo>
<title>Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language Korean</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hakyung</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gyu-Ho</namePart>
<namePart type="family">Shin</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>Findings of the Association for Computational Linguistics: EMNLP 2023</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>This study investigates the extent to which currently available morpheme parsers/taggers apply to lesser-studied languages and language-usage contexts, with a focus on second language (L2) Korean. We pursue this inquiry by (1) training a neural-network model (pre-trained on first language [L1] Korean data) on varying L2 datasets and (2) measuring its morpheme parsing/POS tagging performance on L2 test sets from both the same and different sources of the L2 train sets. Results show that the L2 trained models generally excel in domain-specific tokenization and POS tagging compared to the L1 pre-trained baseline model. Interestingly, increasing the size of the L2 training data does not lead to improving model performance consistently.</abstract>
<identifier type="citekey">sung-shin-2023-diversifying</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.767</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.767/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11461</start>
<end>11473</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language Korean
%A Sung, Hakyung
%A Shin, Gyu-Ho
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sung-shin-2023-diversifying
%X This study investigates the extent to which currently available morpheme parsers/taggers apply to lesser-studied languages and language-usage contexts, with a focus on second language (L2) Korean. We pursue this inquiry by (1) training a neural-network model (pre-trained on first language [L1] Korean data) on varying L2 datasets and (2) measuring its morpheme parsing/POS tagging performance on L2 test sets from both the same and different sources of the L2 train sets. Results show that the L2 trained models generally excel in domain-specific tokenization and POS tagging compared to the L1 pre-trained baseline model. Interestingly, increasing the size of the L2 training data does not lead to improving model performance consistently.
%R 10.18653/v1/2023.findings-emnlp.767
%U https://aclanthology.org/2023.findings-emnlp.767/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.767
%P 11461-11473
Markdown (Informal)
[Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language Korean](https://aclanthology.org/2023.findings-emnlp.767/) (Sung & Shin, Findings 2023)
ACL