@article{sriwirote-etal-2025-thai,
title = "The {T}hai {U}niversal {D}ependency Treebank",
author = "Sriwirote, Panyut and
Leong, Wei Qi and
Polpanumas, Charin and
Thanyawong, Santhawat and
Tjhi, William Chandra and
Aroonmanakun, Wirote and
Rutherford, Attapol T.",
journal = "Transactions of the Association for Computational Linguistics",
volume = "13",
year = "2025",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2025.tacl-1.18/",
doi = "10.1162/tacl_a_00745",
pages = "376--391",
abstract = "Automatic dependency parsing of Thai sentences has been underexplored, as evidenced by the lack of large Thai dependency treebanks with complete dependency structures and the lack of a published evaluation of state-of-the-art models, especially transformer-based parsers. In this work, we addressed these gaps by introducing the Thai Universal Dependency Treebank (TUD), a new Thai treebank consisting of 3,627 trees annotated according to the Universal Dependencies (UD) framework. We then benchmarked 92 dependency parsing models that incorporate pretrained transformers on Thai-PUD and our TUD, achieving state-of-the-art results and shedding light on the optimal model components for Thai dependency parsing. Our error analysis of the models also reveals that polyfunctional words, serial verb construction, and lack of rich morphosyntactic features present main challenges for Thai dependency parsing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sriwirote-etal-2025-thai">
<titleInfo>
<title>The Thai Universal Dependency Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Panyut</namePart>
<namePart type="family">Sriwirote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="given">Qi</namePart>
<namePart type="family">Leong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charin</namePart>
<namePart type="family">Polpanumas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santhawat</namePart>
<namePart type="family">Thanyawong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">Chandra</namePart>
<namePart type="family">Tjhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wirote</namePart>
<namePart type="family">Aroonmanakun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Attapol</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Rutherford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Automatic dependency parsing of Thai sentences has been underexplored, as evidenced by the lack of large Thai dependency treebanks with complete dependency structures and the lack of a published evaluation of state-of-the-art models, especially transformer-based parsers. In this work, we addressed these gaps by introducing the Thai Universal Dependency Treebank (TUD), a new Thai treebank consisting of 3,627 trees annotated according to the Universal Dependencies (UD) framework. We then benchmarked 92 dependency parsing models that incorporate pretrained transformers on Thai-PUD and our TUD, achieving state-of-the-art results and shedding light on the optimal model components for Thai dependency parsing. Our error analysis of the models also reveals that polyfunctional words, serial verb construction, and lack of rich morphosyntactic features present main challenges for Thai dependency parsing.</abstract>
<identifier type="citekey">sriwirote-etal-2025-thai</identifier>
<identifier type="doi">10.1162/tacl_a_00745</identifier>
<location>
<url>https://aclanthology.org/2025.tacl-1.18/</url>
</location>
<part>
<date>2025</date>
<detail type="volume"><number>13</number></detail>
<extent unit="page">
<start>376</start>
<end>391</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T The Thai Universal Dependency Treebank
%A Sriwirote, Panyut
%A Leong, Wei Qi
%A Polpanumas, Charin
%A Thanyawong, Santhawat
%A Tjhi, William Chandra
%A Aroonmanakun, Wirote
%A Rutherford, Attapol T.
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F sriwirote-etal-2025-thai
%X Automatic dependency parsing of Thai sentences has been underexplored, as evidenced by the lack of large Thai dependency treebanks with complete dependency structures and the lack of a published evaluation of state-of-the-art models, especially transformer-based parsers. In this work, we addressed these gaps by introducing the Thai Universal Dependency Treebank (TUD), a new Thai treebank consisting of 3,627 trees annotated according to the Universal Dependencies (UD) framework. We then benchmarked 92 dependency parsing models that incorporate pretrained transformers on Thai-PUD and our TUD, achieving state-of-the-art results and shedding light on the optimal model components for Thai dependency parsing. Our error analysis of the models also reveals that polyfunctional words, serial verb construction, and lack of rich morphosyntactic features present main challenges for Thai dependency parsing.
%R 10.1162/tacl_a_00745
%U https://aclanthology.org/2025.tacl-1.18/
%U https://doi.org/10.1162/tacl_a_00745
%P 376-391
Markdown (Informal)
[The Thai Universal Dependency Treebank](https://aclanthology.org/2025.tacl-1.18/) (Sriwirote et al., TACL 2025)
ACL
- Panyut Sriwirote, Wei Qi Leong, Charin Polpanumas, Santhawat Thanyawong, William Chandra Tjhi, Wirote Aroonmanakun, and Attapol T. Rutherford. 2025. The Thai Universal Dependency Treebank. Transactions of the Association for Computational Linguistics, 13:376–391.