@inproceedings{coto-solano-2022-evaluating,
title = "Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in {B}ribri",
author = "Coto-Solano, Rolando",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.393",
pages = "4455--4467",
abstract = "Word embeddings are critical for numerous NLP tasks but their evaluation in actual under-resourced settings needs further examination. This paper presents a case study in Bribri, a Chibchan language from Costa Rica. Four experiments were adapted from English: Word similarities, WordSim353 correlations, odd-one-out tasks and analogies. Here we discuss their adaptation to an under-resourced Indigenous language and we use them to measure semantic and morphological learning. We trained 96 word2vec models with different hyperparameter combinations. The best models for this under-resourced scenario were Skip-grams with an intermediate size (100 dimensions) and large window sizes (10). These had an average correlation of r=0.28 with WordSim353, a 76{\%} accuracy in semantic odd-one-out and 70{\%} accuracy in structural/morphological odd-one-out. The performance was lower for the analogies: The best models could find the appropriate semantic target amongst the first 25 results approximately 60{\%} of the times, but could only find the morphological/structural target 11{\%} of the times. Future research needs to further explore the patterns of morphological/structural learning, to examine the behavior of deep learning embeddings, and to establish a human baseline. This project seeks to improve Bribri NLP and ultimately help in its maintenance and revitalization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coto-solano-2022-evaluating">
<titleInfo>
<title>Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in Bribri</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rolando</namePart>
<namePart type="family">Coto-Solano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word embeddings are critical for numerous NLP tasks but their evaluation in actual under-resourced settings needs further examination. This paper presents a case study in Bribri, a Chibchan language from Costa Rica. Four experiments were adapted from English: Word similarities, WordSim353 correlations, odd-one-out tasks and analogies. Here we discuss their adaptation to an under-resourced Indigenous language and we use them to measure semantic and morphological learning. We trained 96 word2vec models with different hyperparameter combinations. The best models for this under-resourced scenario were Skip-grams with an intermediate size (100 dimensions) and large window sizes (10). These had an average correlation of r=0.28 with WordSim353, a 76% accuracy in semantic odd-one-out and 70% accuracy in structural/morphological odd-one-out. The performance was lower for the analogies: The best models could find the appropriate semantic target amongst the first 25 results approximately 60% of the times, but could only find the morphological/structural target 11% of the times. Future research needs to further explore the patterns of morphological/structural learning, to examine the behavior of deep learning embeddings, and to establish a human baseline. This project seeks to improve Bribri NLP and ultimately help in its maintenance and revitalization.</abstract>
<identifier type="citekey">coto-solano-2022-evaluating</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.393</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4455</start>
<end>4467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in Bribri
%A Coto-Solano, Rolando
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F coto-solano-2022-evaluating
%X Word embeddings are critical for numerous NLP tasks but their evaluation in actual under-resourced settings needs further examination. This paper presents a case study in Bribri, a Chibchan language from Costa Rica. Four experiments were adapted from English: Word similarities, WordSim353 correlations, odd-one-out tasks and analogies. Here we discuss their adaptation to an under-resourced Indigenous language and we use them to measure semantic and morphological learning. We trained 96 word2vec models with different hyperparameter combinations. The best models for this under-resourced scenario were Skip-grams with an intermediate size (100 dimensions) and large window sizes (10). These had an average correlation of r=0.28 with WordSim353, a 76% accuracy in semantic odd-one-out and 70% accuracy in structural/morphological odd-one-out. The performance was lower for the analogies: The best models could find the appropriate semantic target amongst the first 25 results approximately 60% of the times, but could only find the morphological/structural target 11% of the times. Future research needs to further explore the patterns of morphological/structural learning, to examine the behavior of deep learning embeddings, and to establish a human baseline. This project seeks to improve Bribri NLP and ultimately help in its maintenance and revitalization.
%U https://aclanthology.org/2022.coling-1.393
%P 4455-4467
Markdown (Informal)
[Evaluating Word Embeddings in Extremely Under-Resourced Languages: A Case Study in Bribri](https://aclanthology.org/2022.coling-1.393) (Coto-Solano, COLING 2022)
ACL