@inproceedings{song-xia-2014-modern,
title = "{M}odern {C}hinese Helps Archaic {C}hinese Processing: Finding and Exploiting the Shared Properties",
author = "Song, Yan and
Xia, Fei",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/138_Paper.pdf",
pages = "3129--3136",
abstract = "Languages change over time and ancient languages have been studied in linguistics and other related fields. A main challenge in this research area is the lack of empirical data; for instance, ancient spoken languages often leave little trace of their linguistic properties. From the perspective of natural language processing (NLP), while the NLP community has created dozens of annotated corpora, very few of them are on ancient languages. As an effort toward bridging the gap, we have created a word segmented and POS tagged corpus for Archaic Chinese using articles from Huainanzi, a book written during Chinas Western Han Dynasty (206 BC-9 AD). We then compare this corpus with the Chinese Penn Treebank (CTB), a well-known corpus for Modern Chinese, and report several interesting differences and similarities between the two corpora. Finally, we demonstrate that the CTB can be used to improve the performance of word segmenters and POS taggers for Archaic Chinese, but only through features that have similar behaviors in the two corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-xia-2014-modern">
<titleInfo>
<title>Modern Chinese Helps Archaic Chinese Processing: Finding and Exploiting the Shared Properties</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Languages change over time and ancient languages have been studied in linguistics and other related fields. A main challenge in this research area is the lack of empirical data; for instance, ancient spoken languages often leave little trace of their linguistic properties. From the perspective of natural language processing (NLP), while the NLP community has created dozens of annotated corpora, very few of them are on ancient languages. As an effort toward bridging the gap, we have created a word segmented and POS tagged corpus for Archaic Chinese using articles from Huainanzi, a book written during Chinas Western Han Dynasty (206 BC-9 AD). We then compare this corpus with the Chinese Penn Treebank (CTB), a well-known corpus for Modern Chinese, and report several interesting differences and similarities between the two corpora. Finally, we demonstrate that the CTB can be used to improve the performance of word segmenters and POS taggers for Archaic Chinese, but only through features that have similar behaviors in the two corpora.</abstract>
<identifier type="citekey">song-xia-2014-modern</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/138_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3129</start>
<end>3136</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modern Chinese Helps Archaic Chinese Processing: Finding and Exploiting the Shared Properties
%A Song, Yan
%A Xia, Fei
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F song-xia-2014-modern
%X Languages change over time and ancient languages have been studied in linguistics and other related fields. A main challenge in this research area is the lack of empirical data; for instance, ancient spoken languages often leave little trace of their linguistic properties. From the perspective of natural language processing (NLP), while the NLP community has created dozens of annotated corpora, very few of them are on ancient languages. As an effort toward bridging the gap, we have created a word segmented and POS tagged corpus for Archaic Chinese using articles from Huainanzi, a book written during Chinas Western Han Dynasty (206 BC-9 AD). We then compare this corpus with the Chinese Penn Treebank (CTB), a well-known corpus for Modern Chinese, and report several interesting differences and similarities between the two corpora. Finally, we demonstrate that the CTB can be used to improve the performance of word segmenters and POS taggers for Archaic Chinese, but only through features that have similar behaviors in the two corpora.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/138_Paper.pdf
%P 3129-3136
Markdown (Informal)
[Modern Chinese Helps Archaic Chinese Processing: Finding and Exploiting the Shared Properties](http://www.lrec-conf.org/proceedings/lrec2014/pdf/138_Paper.pdf) (Song & Xia, LREC 2014)
ACL