@inproceedings{aw-etal-2014-talapi,
title = "{T}a{LAP}i {---} A {T}hai Linguistically Annotated Corpus for Language Processing",
author = "Aw, AiTi and
Aljunied, Sharifah Mahani and
Lertcheva, Nattadaporn and
Kalunsima, Sasiwimon",
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/59_Paper.pdf",
pages = "125--132",
abstract = "This paper discusses a Thai corpus, TaLAPi, fully annotated with word segmentation (WS), part-of-speech (POS) and named entity (NE) information with the aim to provide a high-quality and sufficiently large corpus for real-life implementation of Thai language processing tools. The corpus contains 2,720 articles (1,043,471words) from the entertainment and lifestyle (NE{\&}L) domain and 5,489 articles (3,181,487 words) in the news (NEWS) domain, with a total of 35 POS tags and 10 named entity categories. In particular, we present an approach to segment and tag foreign and loan words expressed in transliterated or original form in Thai text corpora. We see this as an area for study as adapted and un-adapted foreign language sequences have not been well addressed in the literature and this poses a challenge to the annotation process due to the increasing use and adoption of foreign words in the Thai language nowadays. To reduce the ambiguities in POS tagging and to provide rich information for facilitating Thai syntactic analysis, we adapted the POS tags used in ORCHID and propose a framework to tag Thai text and also addresses the tagging of loan and foreign words based on the proposed segmentation strategy. TaLAPi also includes a detailed guideline for tagging the 10 named entity categories",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aw-etal-2014-talapi">
<titleInfo>
<title>TaLAPi — A Thai Linguistically Annotated Corpus for Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">AiTi</namePart>
<namePart type="family">Aw</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharifah</namePart>
<namePart type="given">Mahani</namePart>
<namePart type="family">Aljunied</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nattadaporn</namePart>
<namePart type="family">Lertcheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sasiwimon</namePart>
<namePart type="family">Kalunsima</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>This paper discusses a Thai corpus, TaLAPi, fully annotated with word segmentation (WS), part-of-speech (POS) and named entity (NE) information with the aim to provide a high-quality and sufficiently large corpus for real-life implementation of Thai language processing tools. The corpus contains 2,720 articles (1,043,471words) from the entertainment and lifestyle (NE&L) domain and 5,489 articles (3,181,487 words) in the news (NEWS) domain, with a total of 35 POS tags and 10 named entity categories. In particular, we present an approach to segment and tag foreign and loan words expressed in transliterated or original form in Thai text corpora. We see this as an area for study as adapted and un-adapted foreign language sequences have not been well addressed in the literature and this poses a challenge to the annotation process due to the increasing use and adoption of foreign words in the Thai language nowadays. To reduce the ambiguities in POS tagging and to provide rich information for facilitating Thai syntactic analysis, we adapted the POS tags used in ORCHID and propose a framework to tag Thai text and also addresses the tagging of loan and foreign words based on the proposed segmentation strategy. TaLAPi also includes a detailed guideline for tagging the 10 named entity categories</abstract>
<identifier type="citekey">aw-etal-2014-talapi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/59_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>125</start>
<end>132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TaLAPi — A Thai Linguistically Annotated Corpus for Language Processing
%A Aw, AiTi
%A Aljunied, Sharifah Mahani
%A Lertcheva, Nattadaporn
%A Kalunsima, Sasiwimon
%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 aw-etal-2014-talapi
%X This paper discusses a Thai corpus, TaLAPi, fully annotated with word segmentation (WS), part-of-speech (POS) and named entity (NE) information with the aim to provide a high-quality and sufficiently large corpus for real-life implementation of Thai language processing tools. The corpus contains 2,720 articles (1,043,471words) from the entertainment and lifestyle (NE&L) domain and 5,489 articles (3,181,487 words) in the news (NEWS) domain, with a total of 35 POS tags and 10 named entity categories. In particular, we present an approach to segment and tag foreign and loan words expressed in transliterated or original form in Thai text corpora. We see this as an area for study as adapted and un-adapted foreign language sequences have not been well addressed in the literature and this poses a challenge to the annotation process due to the increasing use and adoption of foreign words in the Thai language nowadays. To reduce the ambiguities in POS tagging and to provide rich information for facilitating Thai syntactic analysis, we adapted the POS tags used in ORCHID and propose a framework to tag Thai text and also addresses the tagging of loan and foreign words based on the proposed segmentation strategy. TaLAPi also includes a detailed guideline for tagging the 10 named entity categories
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/59_Paper.pdf
%P 125-132
Markdown (Informal)
[TaLAPi — A Thai Linguistically Annotated Corpus for Language Processing](http://www.lrec-conf.org/proceedings/lrec2014/pdf/59_Paper.pdf) (Aw et al., LREC 2014)
ACL