@inproceedings{jauhiainen-etal-2019-language,
title = "Language and Dialect Identification of Cuneiform Texts",
author = "Jauhiainen, Tommi and
Jauhiainen, Heidi and
Alstola, Tero and
Lind{\'e}n, Krister",
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/W19-1409",
doi = "10.18653/v1/W19-1409",
pages = "89--98",
abstract = "This article introduces a corpus of cuneiform texts from which the dataset for the use of the Cuneiform Language Identification (CLI) 2019 shared task was derived as well as some preliminary language identification experiments conducted using that corpus. We also describe the CLI dataset and how it was derived from the corpus. In addition, we provide some baseline language identification results using the CLI dataset. To the best of our knowledge, the experiments detailed here represent the first time that automatic language identification methods have been used on cuneiform data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jauhiainen-etal-2019-language">
<titleInfo>
<title>Language and Dialect Identification of Cuneiform Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heidi</namePart>
<namePart type="family">Jauhiainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tero</namePart>
<namePart type="family">Alstola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krister</namePart>
<namePart type="family">Lindén</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>This article introduces a corpus of cuneiform texts from which the dataset for the use of the Cuneiform Language Identification (CLI) 2019 shared task was derived as well as some preliminary language identification experiments conducted using that corpus. We also describe the CLI dataset and how it was derived from the corpus. In addition, we provide some baseline language identification results using the CLI dataset. To the best of our knowledge, the experiments detailed here represent the first time that automatic language identification methods have been used on cuneiform data.</abstract>
<identifier type="citekey">jauhiainen-etal-2019-language</identifier>
<identifier type="doi">10.18653/v1/W19-1409</identifier>
<location>
<url>https://aclanthology.org/W19-1409</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>89</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language and Dialect Identification of Cuneiform Texts
%A Jauhiainen, Tommi
%A Jauhiainen, Heidi
%A Alstola, Tero
%A Lindén, Krister
%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 jauhiainen-etal-2019-language
%X This article introduces a corpus of cuneiform texts from which the dataset for the use of the Cuneiform Language Identification (CLI) 2019 shared task was derived as well as some preliminary language identification experiments conducted using that corpus. We also describe the CLI dataset and how it was derived from the corpus. In addition, we provide some baseline language identification results using the CLI dataset. To the best of our knowledge, the experiments detailed here represent the first time that automatic language identification methods have been used on cuneiform data.
%R 10.18653/v1/W19-1409
%U https://aclanthology.org/W19-1409
%U https://doi.org/10.18653/v1/W19-1409
%P 89-98
Markdown (Informal)
[Language and Dialect Identification of Cuneiform Texts](https://aclanthology.org/W19-1409) (Jauhiainen et al., VarDial 2019)
ACL
- Tommi Jauhiainen, Heidi Jauhiainen, Tero Alstola, and Krister Lindén. 2019. Language and Dialect Identification of Cuneiform Texts. In Proceedings of the Sixth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 89–98, Ann Arbor, Michigan. Association for Computational Linguistics.