@inproceedings{gupta-etal-2018-iit,
title = "{IIT} ({BHU}) System for {I}ndo-{A}ryan Language Identification ({ILI}) at {V}ar{D}ial 2018",
author = "Gupta, Divyanshu and
Dhakad, Gourav and
Gupta, Jayprakash and
Singh, Anil Kumar",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Malmasi, Shervin and
Ali, Ahmed},
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Similar Languages, Varieties and Dialects ({V}ar{D}ial 2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3921/",
pages = "185--190",
abstract = "Text language Identification is a Natural Language Processing task of identifying and recognizing a given language out of many different languages from a piece of text. This paper describes our submission to the ILI 2018 shared-task, which includes the identification of 5 closely related Indo-Aryan languages. We developed a word-level LSTM(Long Short-term Memory) model, a specific type of Recurrent Neural Network model, for this task. Given a sentence, our model embeds each word of the sentence and convert into its trainable word embedding, feeds them into our LSTM network and finally predict the language. We obtained an F1 macro score of 0.836, ranking 5th in the task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2018-iit">
<titleInfo>
<title>IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divyanshu</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gourav</namePart>
<namePart type="family">Dhakad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jayprakash</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anil</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)</title>
</titleInfo>
<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">Preslav</namePart>
<namePart type="family">Nakov</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">Shervin</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">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text language Identification is a Natural Language Processing task of identifying and recognizing a given language out of many different languages from a piece of text. This paper describes our submission to the ILI 2018 shared-task, which includes the identification of 5 closely related Indo-Aryan languages. We developed a word-level LSTM(Long Short-term Memory) model, a specific type of Recurrent Neural Network model, for this task. Given a sentence, our model embeds each word of the sentence and convert into its trainable word embedding, feeds them into our LSTM network and finally predict the language. We obtained an F1 macro score of 0.836, ranking 5th in the task.</abstract>
<identifier type="citekey">gupta-etal-2018-iit</identifier>
<location>
<url>https://aclanthology.org/W18-3921/</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>185</start>
<end>190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018
%A Gupta, Divyanshu
%A Dhakad, Gourav
%A Gupta, Jayprakash
%A Singh, Anil Kumar
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Malmasi, Shervin
%Y Ali, Ahmed
%S Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F gupta-etal-2018-iit
%X Text language Identification is a Natural Language Processing task of identifying and recognizing a given language out of many different languages from a piece of text. This paper describes our submission to the ILI 2018 shared-task, which includes the identification of 5 closely related Indo-Aryan languages. We developed a word-level LSTM(Long Short-term Memory) model, a specific type of Recurrent Neural Network model, for this task. Given a sentence, our model embeds each word of the sentence and convert into its trainable word embedding, feeds them into our LSTM network and finally predict the language. We obtained an F1 macro score of 0.836, ranking 5th in the task.
%U https://aclanthology.org/W18-3921/
%P 185-190
Markdown (Informal)
[IIT (BHU) System for Indo-Aryan Language Identification (ILI) at VarDial 2018](https://aclanthology.org/W18-3921/) (Gupta et al., VarDial 2018)
ACL