@inproceedings{williams-dagli-2017-twitter,
title = "{T}witter Language Identification Of Similar Languages And Dialects Without Ground Truth",
author = "Williams, Jennifer and
Dagli, Charlie",
editor = {Nakov, Preslav and
Zampieri, Marcos and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shevin and
Ali, Ahmed},
booktitle = "Proceedings of the Fourth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial)",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1209",
doi = "10.18653/v1/W17-1209",
pages = "73--83",
abstract = "We present a new method to bootstrap filter Twitter language ID labels in our dataset for automatic language identification (LID). Our method combines geo-location, original Twitter LID labels, and Amazon Mechanical Turk to resolve missing and unreliable labels. We are the first to compare LID classification performance using the MIRA algorithm and langid.py. We show classifier performance on different versions of our dataset with high accuracy using only Twitter data, without ground truth, and very few training examples. We also show how Platt Scaling can be use to calibrate MIRA classifier output values into a probability distribution over candidate classes, making the output more intuitive. Our method allows for fine-grained distinctions between similar languages and dialects and allows us to rediscover the language composition of our Twitter dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="williams-dagli-2017-twitter">
<titleInfo>
<title>Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlie</namePart>
<namePart type="family">Dagli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shevin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a new method to bootstrap filter Twitter language ID labels in our dataset for automatic language identification (LID). Our method combines geo-location, original Twitter LID labels, and Amazon Mechanical Turk to resolve missing and unreliable labels. We are the first to compare LID classification performance using the MIRA algorithm and langid.py. We show classifier performance on different versions of our dataset with high accuracy using only Twitter data, without ground truth, and very few training examples. We also show how Platt Scaling can be use to calibrate MIRA classifier output values into a probability distribution over candidate classes, making the output more intuitive. Our method allows for fine-grained distinctions between similar languages and dialects and allows us to rediscover the language composition of our Twitter dataset.</abstract>
<identifier type="citekey">williams-dagli-2017-twitter</identifier>
<identifier type="doi">10.18653/v1/W17-1209</identifier>
<location>
<url>https://aclanthology.org/W17-1209</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>73</start>
<end>83</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth
%A Williams, Jennifer
%A Dagli, Charlie
%Y Nakov, Preslav
%Y Zampieri, Marcos
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shevin
%Y Ali, Ahmed
%S Proceedings of the Fourth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F williams-dagli-2017-twitter
%X We present a new method to bootstrap filter Twitter language ID labels in our dataset for automatic language identification (LID). Our method combines geo-location, original Twitter LID labels, and Amazon Mechanical Turk to resolve missing and unreliable labels. We are the first to compare LID classification performance using the MIRA algorithm and langid.py. We show classifier performance on different versions of our dataset with high accuracy using only Twitter data, without ground truth, and very few training examples. We also show how Platt Scaling can be use to calibrate MIRA classifier output values into a probability distribution over candidate classes, making the output more intuitive. Our method allows for fine-grained distinctions between similar languages and dialects and allows us to rediscover the language composition of our Twitter dataset.
%R 10.18653/v1/W17-1209
%U https://aclanthology.org/W17-1209
%U https://doi.org/10.18653/v1/W17-1209
%P 73-83
Markdown (Informal)
[Twitter Language Identification Of Similar Languages And Dialects Without Ground Truth](https://aclanthology.org/W17-1209) (Williams & Dagli, VarDial 2017)
ACL