@inproceedings{thu-etal-2016-introducing,
title = "Introducing the {A}sian Language Treebank ({ALT})",
author = "Thu, Ye Kyaw and
Pa, Win Pa and
Utiyama, Masao and
Finch, Andrew and
Sumita, Eiichiro",
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/L16-1249",
pages = "1574--1578",
abstract = "This paper introduces the ALT project initiated by the Advanced Speech Translation Research and Development Promotion Center (ASTREC), NICT, Kyoto, Japan. The aim of this project is to accelerate NLP research for Asian languages such as Indonesian, Japanese, Khmer, Laos, Malay, Myanmar, Philippine, Thai and Vietnamese. The original resource for this project was English articles that were randomly selected from Wikinews. The project has so far created a corpus for Myanmar and will extend in scope to include other languages in the near future. A 20000-sentence corpus of Myanmar that has been manually translated from an English corpus has been word segmented, word aligned, part-of-speech tagged and constituency parsed by human annotators. In this paper, we present the implementation steps for creating the treebank in detail, including a description of the ALT web-based treebanking tool. Moreover, we report statistics on the annotation quality of the Myanmar treebank created so far.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thu-etal-2016-introducing">
<titleInfo>
<title>Introducing the Asian Language Treebank (ALT)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="given">Kyaw</namePart>
<namePart type="family">Thu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Win</namePart>
<namePart type="given">Pa</namePart>
<namePart type="family">Pa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Finch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</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>This paper introduces the ALT project initiated by the Advanced Speech Translation Research and Development Promotion Center (ASTREC), NICT, Kyoto, Japan. The aim of this project is to accelerate NLP research for Asian languages such as Indonesian, Japanese, Khmer, Laos, Malay, Myanmar, Philippine, Thai and Vietnamese. The original resource for this project was English articles that were randomly selected from Wikinews. The project has so far created a corpus for Myanmar and will extend in scope to include other languages in the near future. A 20000-sentence corpus of Myanmar that has been manually translated from an English corpus has been word segmented, word aligned, part-of-speech tagged and constituency parsed by human annotators. In this paper, we present the implementation steps for creating the treebank in detail, including a description of the ALT web-based treebanking tool. Moreover, we report statistics on the annotation quality of the Myanmar treebank created so far.</abstract>
<identifier type="citekey">thu-etal-2016-introducing</identifier>
<location>
<url>https://aclanthology.org/L16-1249</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1574</start>
<end>1578</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing the Asian Language Treebank (ALT)
%A Thu, Ye Kyaw
%A Pa, Win Pa
%A Utiyama, Masao
%A Finch, Andrew
%A Sumita, Eiichiro
%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 thu-etal-2016-introducing
%X This paper introduces the ALT project initiated by the Advanced Speech Translation Research and Development Promotion Center (ASTREC), NICT, Kyoto, Japan. The aim of this project is to accelerate NLP research for Asian languages such as Indonesian, Japanese, Khmer, Laos, Malay, Myanmar, Philippine, Thai and Vietnamese. The original resource for this project was English articles that were randomly selected from Wikinews. The project has so far created a corpus for Myanmar and will extend in scope to include other languages in the near future. A 20000-sentence corpus of Myanmar that has been manually translated from an English corpus has been word segmented, word aligned, part-of-speech tagged and constituency parsed by human annotators. In this paper, we present the implementation steps for creating the treebank in detail, including a description of the ALT web-based treebanking tool. Moreover, we report statistics on the annotation quality of the Myanmar treebank created so far.
%U https://aclanthology.org/L16-1249
%P 1574-1578
Markdown (Informal)
[Introducing the Asian Language Treebank (ALT)](https://aclanthology.org/L16-1249) (Thu et al., LREC 2016)
ACL
- Ye Kyaw Thu, Win Pa Pa, Masao Utiyama, Andrew Finch, and Eiichiro Sumita. 2016. Introducing the Asian Language Treebank (ALT). In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1574–1578, Portorož, Slovenia. European Language Resources Association (ELRA).