Naive Bayes-based Experiments in Romanian Dialect Identification

Tommi Jauhiainen; Heidi Jauhiainen; Krister Linden

Naive Bayes-based Experiments in Romanian Dialect Identification

Tommi Jauhiainen, Heidi Jauhiainen, Krister Linden

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

Abstrakti

This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.

Alkuperäiskieli	englanti
Otsikko	Proceedings of the 8th VarDial Workshop on NLP for Similar Languages, Varieties and Dialects
Toimittajat	Marcos Zampieri, Preslav Nakov, Nikola Ljubešic, Jörg Tiedemann , Yves Scherrer , Tommi Jauhiainen
Sivumäärä	8
Julkaisupaikka	Stroudsburg
Kustantaja	ACL Anthology
Julkaisupäivä	2021
Sivut	76-83
ISBN (elektroninen)	978-1-954085-12-1
Tila	Julkaistu - 2021
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	Eight workshop on NLP for similar languages, varieties and dialects (VarDial 2021) - [Virtual event] Kesto: 20 huhtik. 2021 → 20 huhtik. 2021 Konferenssinumero: 8 https://sites.google.com/view/vardial2021

Tieteenalat

6121 Kielitieteet
113 Tietojenkäsittely- ja informaatiotieteet

Pääsy asiakirjaan

2021.vardial-1.9Lopullinen julkaistu versio, 269 KBLisenssi: CC BY

Siteeraa tätä

Jauhiainen, Tommi ; Jauhiainen, Heidi ; Linden, Krister. / Naive Bayes-based Experiments in Romanian Dialect Identification. Proceedings of the 8th VarDial Workshop on NLP for Similar Languages, Varieties and Dialects. Toimittaja / Marcos Zampieri ; Preslav Nakov ; Nikola Ljubešic ; Jörg Tiedemann ; Yves Scherrer ; Tommi Jauhiainen. Stroudsburg : ACL Anthology, 2021. Sivut 76-83

@inproceedings{b7a2693e61f84b42aae0340e7cc8dff5,

title = "Naive Bayes-based Experiments in Romanian Dialect Identification",

abstract = "This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.",

keywords = "6121 Languages, 113 Computer and information sciences",

author = "Tommi Jauhiainen and Heidi Jauhiainen and Krister Linden",

year = "2021",

language = "English",

pages = "76--83",

editor = "Zampieri, {Marcos } and Nakov, {Preslav } and Ljube{\v s}ic, {Nikola } and {Tiedemann }, {J{\"o}rg } and {Scherrer }, {Yves } and Tommi Jauhiainen",

booktitle = "Proceedings of the 8th VarDial Workshop on NLP for Similar Languages, Varieties and Dialects",

publisher = "ACL Anthology",

address = "United States",

note = "Workshop on NLP for similar languages, varieties and dialects, VarDial 2021 ; Conference date: 20-04-2021 Through 20-04-2021",

url = "https://sites.google.com/view/vardial2021",

}

Jauhiainen, T , Jauhiainen, H & Linden, K 2021, Naive Bayes-based Experiments in Romanian Dialect Identification. julkaisussa M Zampieri, P Nakov, N Ljubešic, J Tiedemann , Y Scherrer & T Jauhiainen (toim), Proceedings of the 8th VarDial Workshop on NLP for Similar Languages, Varieties and Dialects. ACL Anthology, Stroudsburg, Sivut 76-83, Eight workshop on NLP for similar languages, varieties and dialects (VarDial 2021), 20/04/2021.

Naive Bayes-based Experiments in Romanian Dialect Identification. / Jauhiainen, Tommi ; Jauhiainen, Heidi ; Linden, Krister.

Proceedings of the 8th VarDial Workshop on NLP for Similar Languages, Varieties and Dialects. toim. / Marcos Zampieri; Preslav Nakov; Nikola Ljubešic; Jörg Tiedemann ; Yves Scherrer ; Tommi Jauhiainen. Stroudsburg : ACL Anthology, 2021. s. 76-83.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

TY - GEN

T1 - Naive Bayes-based Experiments in Romanian Dialect Identification

AU - Jauhiainen, Tommi

AU - Jauhiainen, Heidi

AU - Linden, Krister

N1 - Conference code: 8

PY - 2021

Y1 - 2021

N2 - This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.

AB - This article describes the experiments and systems developed by the SUKI team for the second edition of the Romanian Dialect Identification (RDI) shared task which was organized as part of the 2021 VarDial Evaluation Campaign. We submitted two runs to the shared task and our second submission was the overall best submission by a noticeable margin. Our best submission used a character n-gram based naive Bayes classifier with adaptive language models. We describe our experiments on the development set leading to both submissions.

KW - 6121 Languages

KW - 113 Computer and information sciences

M3 - Conference contribution

SP - 76

EP - 83

BT - Proceedings of the 8th VarDial Workshop on NLP for Similar Languages, Varieties and Dialects

A2 - Zampieri, Marcos

A2 - Nakov, Preslav

A2 - Ljubešic, Nikola

A2 - Tiedemann , Jörg

A2 - Scherrer , Yves

A2 - Jauhiainen, Tommi

PB - ACL Anthology

CY - Stroudsburg

T2 - Workshop on NLP for similar languages, varieties and dialects

Y2 - 20 April 2021 through 20 April 2021

ER -