@inproceedings{peng-etal-2022-gcdt,
title = "{GCDT}: A {C}hinese {RST} Treebank for Multigenre and Multilingual Discourse Parsing",
author = "Peng, Siyao and
Liu, Yang Janet and
Zeldes, Amir",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.47",
pages = "382--391",
abstract = "A lack of large-scale human-annotated data has hampered the hierarchical discourse parsing of Chinese. In this paper, we present GCDT, the largest hierarchical discourse treebank for Mandarin Chinese in the framework of Rhetorical Structure Theory (RST). GCDT covers over 60K tokens across five genres of freely available text, using the same relation inventory as contemporary RST treebanks for English. We also report on this dataset{'}s parsing experiments, including state-of-the-art (SOTA) scores for Chinese RST parsing and RST parsing on the English GUM dataset, using cross-lingual training in Chinese and English with multilingual embeddings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-etal-2022-gcdt">
<titleInfo>
<title>GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyao</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">Janet</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zeldes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</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">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A lack of large-scale human-annotated data has hampered the hierarchical discourse parsing of Chinese. In this paper, we present GCDT, the largest hierarchical discourse treebank for Mandarin Chinese in the framework of Rhetorical Structure Theory (RST). GCDT covers over 60K tokens across five genres of freely available text, using the same relation inventory as contemporary RST treebanks for English. We also report on this dataset’s parsing experiments, including state-of-the-art (SOTA) scores for Chinese RST parsing and RST parsing on the English GUM dataset, using cross-lingual training in Chinese and English with multilingual embeddings.</abstract>
<identifier type="citekey">peng-etal-2022-gcdt</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.47</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>382</start>
<end>391</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing
%A Peng, Siyao
%A Liu, Yang Janet
%A Zeldes, Amir
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F peng-etal-2022-gcdt
%X A lack of large-scale human-annotated data has hampered the hierarchical discourse parsing of Chinese. In this paper, we present GCDT, the largest hierarchical discourse treebank for Mandarin Chinese in the framework of Rhetorical Structure Theory (RST). GCDT covers over 60K tokens across five genres of freely available text, using the same relation inventory as contemporary RST treebanks for English. We also report on this dataset’s parsing experiments, including state-of-the-art (SOTA) scores for Chinese RST parsing and RST parsing on the English GUM dataset, using cross-lingual training in Chinese and English with multilingual embeddings.
%U https://aclanthology.org/2022.aacl-short.47
%P 382-391
Markdown (Informal)
[GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing](https://aclanthology.org/2022.aacl-short.47) (Peng et al., AACL-IJCNLP 2022)
ACL
- Siyao Peng, Yang Janet Liu, and Amir Zeldes. 2022. GCDT: A Chinese RST Treebank for Multigenre and Multilingual Discourse Parsing. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 382–391, Online only. Association for Computational Linguistics.