@inproceedings{doostmohammadi-nassajian-2019-investigating,
title = "Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts",
author = "Doostmohammadi, Ehsan and
Nassajian, Minoo",
editor = {Zampieri, Marcos and
Nakov, Preslav and
Malmasi, Shervin and
Ljube{\v{s}}i{\'c}, Nikola and
Tiedemann, J{\"o}rg and
Ali, Ahmed},
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Similar Languages, Varieties and Dialects",
month = jun,
year = "2019",
address = "Ann Arbor, Michigan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1420",
doi = "10.18653/v1/W19-1420",
pages = "188--193",
abstract = "Identification of the languages written using cuneiform symbols is a difficult task due to the lack of resources and the problem of tokenization. The Cuneiform Language Identification task in VarDial 2019 addresses the problem of identifying seven languages and dialects written in cuneiform; Sumerian and six dialects of Akkadian language: Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian. This paper describes the approaches taken by SharifCL team to this problem in VarDial 2019. The best result belongs to an ensemble of Support Vector Machines and a naive Bayes classifier, both working on character-level features, with macro-averaged F1-score of 72.10{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="doostmohammadi-nassajian-2019-investigating">
<titleInfo>
<title>Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Doostmohammadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minoo</namePart>
<namePart type="family">Nassajian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects</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">Shervin</namePart>
<namePart type="family">Malmasi</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">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">Ann Arbor, Michigan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identification of the languages written using cuneiform symbols is a difficult task due to the lack of resources and the problem of tokenization. The Cuneiform Language Identification task in VarDial 2019 addresses the problem of identifying seven languages and dialects written in cuneiform; Sumerian and six dialects of Akkadian language: Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian. This paper describes the approaches taken by SharifCL team to this problem in VarDial 2019. The best result belongs to an ensemble of Support Vector Machines and a naive Bayes classifier, both working on character-level features, with macro-averaged F1-score of 72.10%.</abstract>
<identifier type="citekey">doostmohammadi-nassajian-2019-investigating</identifier>
<identifier type="doi">10.18653/v1/W19-1420</identifier>
<location>
<url>https://aclanthology.org/W19-1420</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>188</start>
<end>193</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts
%A Doostmohammadi, Ehsan
%A Nassajian, Minoo
%Y Zampieri, Marcos
%Y Nakov, Preslav
%Y Malmasi, Shervin
%Y Ljubešić, Nikola
%Y Tiedemann, Jörg
%Y Ali, Ahmed
%S Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects
%D 2019
%8 June
%I Association for Computational Linguistics
%C Ann Arbor, Michigan
%F doostmohammadi-nassajian-2019-investigating
%X Identification of the languages written using cuneiform symbols is a difficult task due to the lack of resources and the problem of tokenization. The Cuneiform Language Identification task in VarDial 2019 addresses the problem of identifying seven languages and dialects written in cuneiform; Sumerian and six dialects of Akkadian language: Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian. This paper describes the approaches taken by SharifCL team to this problem in VarDial 2019. The best result belongs to an ensemble of Support Vector Machines and a naive Bayes classifier, both working on character-level features, with macro-averaged F1-score of 72.10%.
%R 10.18653/v1/W19-1420
%U https://aclanthology.org/W19-1420
%U https://doi.org/10.18653/v1/W19-1420
%P 188-193
Markdown (Informal)
[Investigating Machine Learning Methods for Language and Dialect Identification of Cuneiform Texts](https://aclanthology.org/W19-1420) (Doostmohammadi & Nassajian, VarDial 2019)
ACL