@inproceedings{tursun-cakici-2017-noisy,
title = "Noisy {U}yghur Text Normalization",
author = "Tursun, Osman and
Cakici, Ruket",
editor = "Derczynski, Leon and
Xu, Wei and
Ritter, Alan and
Baldwin, Tim",
booktitle = "Proceedings of the 3rd Workshop on Noisy User-generated Text",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-4412",
doi = "10.18653/v1/W17-4412",
pages = "85--93",
abstract = "Uyghur is the second largest and most actively used social media language in China. However, a non-negligible part of Uyghur text appearing in social media is unsystematically written with the Latin alphabet, and it continues to increase in size. Uyghur text in this format is incomprehensible and ambiguous even to native Uyghur speakers. In addition, Uyghur texts in this form lack the potential for any kind of advancement for the NLP tasks related to the Uyghur language. Restoring and preventing noisy Uyghur text written with unsystematic Latin alphabets will be essential to the protection of Uyghur language and improving the accuracy of Uyghur NLP tasks. To this purpose, in this work we propose and compare the noisy channel model and the neural encoder-decoder model as normalizing methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tursun-cakici-2017-noisy">
<titleInfo>
<title>Noisy Uyghur Text Normalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="family">Tursun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruket</namePart>
<namePart type="family">Cakici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Noisy User-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Uyghur is the second largest and most actively used social media language in China. However, a non-negligible part of Uyghur text appearing in social media is unsystematically written with the Latin alphabet, and it continues to increase in size. Uyghur text in this format is incomprehensible and ambiguous even to native Uyghur speakers. In addition, Uyghur texts in this form lack the potential for any kind of advancement for the NLP tasks related to the Uyghur language. Restoring and preventing noisy Uyghur text written with unsystematic Latin alphabets will be essential to the protection of Uyghur language and improving the accuracy of Uyghur NLP tasks. To this purpose, in this work we propose and compare the noisy channel model and the neural encoder-decoder model as normalizing methods.</abstract>
<identifier type="citekey">tursun-cakici-2017-noisy</identifier>
<identifier type="doi">10.18653/v1/W17-4412</identifier>
<location>
<url>https://aclanthology.org/W17-4412</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>85</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Noisy Uyghur Text Normalization
%A Tursun, Osman
%A Cakici, Ruket
%Y Derczynski, Leon
%Y Xu, Wei
%Y Ritter, Alan
%Y Baldwin, Tim
%S Proceedings of the 3rd Workshop on Noisy User-generated Text
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F tursun-cakici-2017-noisy
%X Uyghur is the second largest and most actively used social media language in China. However, a non-negligible part of Uyghur text appearing in social media is unsystematically written with the Latin alphabet, and it continues to increase in size. Uyghur text in this format is incomprehensible and ambiguous even to native Uyghur speakers. In addition, Uyghur texts in this form lack the potential for any kind of advancement for the NLP tasks related to the Uyghur language. Restoring and preventing noisy Uyghur text written with unsystematic Latin alphabets will be essential to the protection of Uyghur language and improving the accuracy of Uyghur NLP tasks. To this purpose, in this work we propose and compare the noisy channel model and the neural encoder-decoder model as normalizing methods.
%R 10.18653/v1/W17-4412
%U https://aclanthology.org/W17-4412
%U https://doi.org/10.18653/v1/W17-4412
%P 85-93
Markdown (Informal)
[Noisy Uyghur Text Normalization](https://aclanthology.org/W17-4412) (Tursun & Cakici, WNUT 2017)
ACL
- Osman Tursun and Ruket Cakici. 2017. Noisy Uyghur Text Normalization. In Proceedings of the 3rd Workshop on Noisy User-generated Text, pages 85–93, Copenhagen, Denmark. Association for Computational Linguistics.