@inproceedings{koksal-etal-2020-turki,
title = "{\#}Turki{\$}h{T}weets: A Benchmark Dataset for {T}urkish Text Correction",
author = {Koksal, Asiye Tuba and
Bozal, Ozge and
Y{\"u}rekli, Emre and
Gezici, Gizem},
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.374",
doi = "10.18653/v1/2020.findings-emnlp.374",
pages = "4190--4198",
abstract = "{\#}Turki{\$}hTweets is a benchmark dataset for the task of correcting the user misspellings, with the purpose of introducing the first public Turkish dataset in this area. {\#}Turki{\$}hTweets provides correct/incorrect word annotations with a detailed misspelling category formulation based on the real user data. We evaluated four state-of-the-art approaches on our dataset to present a preliminary analysis for the sake of reproducibility.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koksal-etal-2020-turki">
<titleInfo>
<title>#Turki$hTweets: A Benchmark Dataset for Turkish Text Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asiye</namePart>
<namePart type="given">Tuba</namePart>
<namePart type="family">Koksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozge</namePart>
<namePart type="family">Bozal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emre</namePart>
<namePart type="family">Yürekli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gizem</namePart>
<namePart type="family">Gezici</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>#Turki$hTweets is a benchmark dataset for the task of correcting the user misspellings, with the purpose of introducing the first public Turkish dataset in this area. #Turki$hTweets provides correct/incorrect word annotations with a detailed misspelling category formulation based on the real user data. We evaluated four state-of-the-art approaches on our dataset to present a preliminary analysis for the sake of reproducibility.</abstract>
<identifier type="citekey">koksal-etal-2020-turki</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.374</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.374</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4190</start>
<end>4198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T #Turki$hTweets: A Benchmark Dataset for Turkish Text Correction
%A Koksal, Asiye Tuba
%A Bozal, Ozge
%A Yürekli, Emre
%A Gezici, Gizem
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F koksal-etal-2020-turki
%X #Turki$hTweets is a benchmark dataset for the task of correcting the user misspellings, with the purpose of introducing the first public Turkish dataset in this area. #Turki$hTweets provides correct/incorrect word annotations with a detailed misspelling category formulation based on the real user data. We evaluated four state-of-the-art approaches on our dataset to present a preliminary analysis for the sake of reproducibility.
%R 10.18653/v1/2020.findings-emnlp.374
%U https://aclanthology.org/2020.findings-emnlp.374
%U https://doi.org/10.18653/v1/2020.findings-emnlp.374
%P 4190-4198
Markdown (Informal)
[#Turki$hTweets: A Benchmark Dataset for Turkish Text Correction](https://aclanthology.org/2020.findings-emnlp.374) (Koksal et al., Findings 2020)
ACL