@inproceedings{arreerard-etal-2022-survey,
title = "Survey on {T}hai {NLP} Language Resources and Tools",
author = "Arreerard, Ratchakrit and
Mander, Stephen and
Piao, Scott",
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-1.697",
pages = "6495--6505",
abstract = "Over the past decades, Natural Language Processing (NLP) research has been expanding to cover more languages. Recently particularly, NLP community has paid increasing attention to under-resourced languages. However, there are still many languages for which NLP research is limited in terms of both language resources and software tools. Thai language is one of the under-resourced languages in the NLP domain, although it is spoken by nearly 70 million people globally. In this paper, we report on our survey on the past development of Thai NLP research to help understand its current state and future research directions. Our survey shows that, although Thai NLP community has achieved a significant achievement over the past three decades, particularly on NLP upstream tasks such as tokenisation, research on downstream tasks such as syntactic parsing and semantic analysis is still limited. But we foresee that Thai NLP research will advance rapidly as richer Thai language resources and more robust NLP techniques become available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arreerard-etal-2022-survey">
<titleInfo>
<title>Survey on Thai NLP Language Resources and Tools</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ratchakrit</namePart>
<namePart type="family">Arreerard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Mander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Piao</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>Over the past decades, Natural Language Processing (NLP) research has been expanding to cover more languages. Recently particularly, NLP community has paid increasing attention to under-resourced languages. However, there are still many languages for which NLP research is limited in terms of both language resources and software tools. Thai language is one of the under-resourced languages in the NLP domain, although it is spoken by nearly 70 million people globally. In this paper, we report on our survey on the past development of Thai NLP research to help understand its current state and future research directions. Our survey shows that, although Thai NLP community has achieved a significant achievement over the past three decades, particularly on NLP upstream tasks such as tokenisation, research on downstream tasks such as syntactic parsing and semantic analysis is still limited. But we foresee that Thai NLP research will advance rapidly as richer Thai language resources and more robust NLP techniques become available.</abstract>
<identifier type="citekey">arreerard-etal-2022-survey</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.697</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6495</start>
<end>6505</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Survey on Thai NLP Language Resources and Tools
%A Arreerard, Ratchakrit
%A Mander, Stephen
%A Piao, Scott
%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 arreerard-etal-2022-survey
%X Over the past decades, Natural Language Processing (NLP) research has been expanding to cover more languages. Recently particularly, NLP community has paid increasing attention to under-resourced languages. However, there are still many languages for which NLP research is limited in terms of both language resources and software tools. Thai language is one of the under-resourced languages in the NLP domain, although it is spoken by nearly 70 million people globally. In this paper, we report on our survey on the past development of Thai NLP research to help understand its current state and future research directions. Our survey shows that, although Thai NLP community has achieved a significant achievement over the past three decades, particularly on NLP upstream tasks such as tokenisation, research on downstream tasks such as syntactic parsing and semantic analysis is still limited. But we foresee that Thai NLP research will advance rapidly as richer Thai language resources and more robust NLP techniques become available.
%U https://aclanthology.org/2022.lrec-1.697
%P 6495-6505
Markdown (Informal)
[Survey on Thai NLP Language Resources and Tools](https://aclanthology.org/2022.lrec-1.697) (Arreerard et al., LREC 2022)
ACL
- Ratchakrit Arreerard, Stephen Mander, and Scott Piao. 2022. Survey on Thai NLP Language Resources and Tools. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6495–6505, Marseille, France. European Language Resources Association.