@inproceedings{oh-etal-2020-analysis,
title = "Analysis of the {P}enn {K}orean {U}niversal {D}ependency Treebank ({PKT}-{UD}): Manual Revision to Build Robust Parsing Model in {K}orean",
author = "Oh, Tae Hwan and
Han, Ji Yoon and
Choe, Hyonsu and
Park, Seokwon and
He, Han and
Choi, Jinho D. and
Han, Na-Rae and
Hwang, Jena D. and
Kim, Hansaem",
editor = "Bouma, Gosse and
Matsumoto, Yuji and
Oepen, Stephan and
Sagae, Kenji and
Seddah, Djam{\'e} and
Sun, Weiwei and
S{\o}gaard, Anders and
Tsarfaty, Reut and
Zeman, Dan",
booktitle = "Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.iwpt-1.13",
doi = "10.18653/v1/2020.iwpt-1.13",
pages = "122--131",
abstract = "In this paper, we first open on important issues regarding the Penn Korean Universal Treebank (PKT-UD) and address these issues by revising the entire corpus manually with the aim of producing cleaner UD annotations that are more faithful to Korean grammar. For compatibility to the rest of UD corpora, we follow the UDv2 guidelines, and extensively revise the part-of-speech tags and the dependency relations to reflect morphological features and flexible word- order aspects in Korean. The original and the revised versions of PKT-UD are experimented with transformer-based parsing models using biaffine attention. The parsing model trained on the revised corpus shows a significant improvement of 3.0{\%} in labeled attachment score over the model trained on the previous corpus. Our error analysis demonstrates that this revision allows the parsing model to learn relations more robustly, reducing several critical errors that used to be made by the previous model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oh-etal-2020-analysis">
<titleInfo>
<title>Analysis of the Penn Korean Universal Dependency Treebank (PKT-UD): Manual Revision to Build Robust Parsing Model in Korean</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tae</namePart>
<namePart type="given">Hwan</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="given">Yoon</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyonsu</namePart>
<namePart type="family">Choe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokwon</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Na-Rae</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jena</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gosse</namePart>
<namePart type="family">Bouma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Oepen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Sagae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiwei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we first open on important issues regarding the Penn Korean Universal Treebank (PKT-UD) and address these issues by revising the entire corpus manually with the aim of producing cleaner UD annotations that are more faithful to Korean grammar. For compatibility to the rest of UD corpora, we follow the UDv2 guidelines, and extensively revise the part-of-speech tags and the dependency relations to reflect morphological features and flexible word- order aspects in Korean. The original and the revised versions of PKT-UD are experimented with transformer-based parsing models using biaffine attention. The parsing model trained on the revised corpus shows a significant improvement of 3.0% in labeled attachment score over the model trained on the previous corpus. Our error analysis demonstrates that this revision allows the parsing model to learn relations more robustly, reducing several critical errors that used to be made by the previous model.</abstract>
<identifier type="citekey">oh-etal-2020-analysis</identifier>
<identifier type="doi">10.18653/v1/2020.iwpt-1.13</identifier>
<location>
<url>https://aclanthology.org/2020.iwpt-1.13</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>122</start>
<end>131</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analysis of the Penn Korean Universal Dependency Treebank (PKT-UD): Manual Revision to Build Robust Parsing Model in Korean
%A Oh, Tae Hwan
%A Han, Ji Yoon
%A Choe, Hyonsu
%A Park, Seokwon
%A He, Han
%A Choi, Jinho D.
%A Han, Na-Rae
%A Hwang, Jena D.
%A Kim, Hansaem
%Y Bouma, Gosse
%Y Matsumoto, Yuji
%Y Oepen, Stephan
%Y Sagae, Kenji
%Y Seddah, Djamé
%Y Sun, Weiwei
%Y Søgaard, Anders
%Y Tsarfaty, Reut
%Y Zeman, Dan
%S Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F oh-etal-2020-analysis
%X In this paper, we first open on important issues regarding the Penn Korean Universal Treebank (PKT-UD) and address these issues by revising the entire corpus manually with the aim of producing cleaner UD annotations that are more faithful to Korean grammar. For compatibility to the rest of UD corpora, we follow the UDv2 guidelines, and extensively revise the part-of-speech tags and the dependency relations to reflect morphological features and flexible word- order aspects in Korean. The original and the revised versions of PKT-UD are experimented with transformer-based parsing models using biaffine attention. The parsing model trained on the revised corpus shows a significant improvement of 3.0% in labeled attachment score over the model trained on the previous corpus. Our error analysis demonstrates that this revision allows the parsing model to learn relations more robustly, reducing several critical errors that used to be made by the previous model.
%R 10.18653/v1/2020.iwpt-1.13
%U https://aclanthology.org/2020.iwpt-1.13
%U https://doi.org/10.18653/v1/2020.iwpt-1.13
%P 122-131
Markdown (Informal)
[Analysis of the Penn Korean Universal Dependency Treebank (PKT-UD): Manual Revision to Build Robust Parsing Model in Korean](https://aclanthology.org/2020.iwpt-1.13) (Oh et al., IWPT 2020)
ACL
- Tae Hwan Oh, Ji Yoon Han, Hyonsu Choe, Seokwon Park, Han He, Jinho D. Choi, Na-Rae Han, Jena D. Hwang, and Hansaem Kim. 2020. Analysis of the Penn Korean Universal Dependency Treebank (PKT-UD): Manual Revision to Build Robust Parsing Model in Korean. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 122–131, Online. Association for Computational Linguistics.