@inproceedings{wong-lee-2016-dependency,
title = "A Dependency Treebank of the {C}hinese Buddhist Canon",
author = "Wong, Tak-sum and
Lee, John",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1265",
pages = "1679--1683",
abstract = "We present a dependency treebank of the Chinese Buddhist Canon, which contains 1,514 texts with about 50 million Chinese characters. The treebank was created by an automatic parser trained on a smaller treebank, containing four manually annotated sutras (Lee and Kong, 2014). We report results on word segmentation, part-of-speech tagging and dependency parsing, and discuss challenges posed by the processing of medieval Chinese. In a case study, we exploit the treebank to examine verbs frequently associated with Buddha, and to analyze usage patterns of quotative verbs in direct speech. Our results suggest that certain quotative verbs imply status differences between the speaker and the listener.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wong-lee-2016-dependency">
<titleInfo>
<title>A Dependency Treebank of the Chinese Buddhist Canon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tak-sum</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a dependency treebank of the Chinese Buddhist Canon, which contains 1,514 texts with about 50 million Chinese characters. The treebank was created by an automatic parser trained on a smaller treebank, containing four manually annotated sutras (Lee and Kong, 2014). We report results on word segmentation, part-of-speech tagging and dependency parsing, and discuss challenges posed by the processing of medieval Chinese. In a case study, we exploit the treebank to examine verbs frequently associated with Buddha, and to analyze usage patterns of quotative verbs in direct speech. Our results suggest that certain quotative verbs imply status differences between the speaker and the listener.</abstract>
<identifier type="citekey">wong-lee-2016-dependency</identifier>
<location>
<url>https://aclanthology.org/L16-1265</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1679</start>
<end>1683</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dependency Treebank of the Chinese Buddhist Canon
%A Wong, Tak-sum
%A Lee, John
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F wong-lee-2016-dependency
%X We present a dependency treebank of the Chinese Buddhist Canon, which contains 1,514 texts with about 50 million Chinese characters. The treebank was created by an automatic parser trained on a smaller treebank, containing four manually annotated sutras (Lee and Kong, 2014). We report results on word segmentation, part-of-speech tagging and dependency parsing, and discuss challenges posed by the processing of medieval Chinese. In a case study, we exploit the treebank to examine verbs frequently associated with Buddha, and to analyze usage patterns of quotative verbs in direct speech. Our results suggest that certain quotative verbs imply status differences between the speaker and the listener.
%U https://aclanthology.org/L16-1265
%P 1679-1683
Markdown (Informal)
[A Dependency Treebank of the Chinese Buddhist Canon](https://aclanthology.org/L16-1265) (Wong & Lee, LREC 2016)
ACL
- Tak-sum Wong and John Lee. 2016. A Dependency Treebank of the Chinese Buddhist Canon. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1679–1683, Portorož, Slovenia. European Language Resources Association (ELRA).