@inproceedings{jauhiainen-etal-2022-optimizing,
title = "Optimizing Naive {B}ayes for {A}rabic Dialect Identification",
author = "Jauhiainen, Tommi and
Jauhiainen, Heidi and
Lind{\'e}n, Krister",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.40",
doi = "10.18653/v1/2022.wanlp-1.40",
pages = "409--414",
abstract = "This article describes the language identification system used by the SUKI team in the 2022 Nuanced Arabic Dialect Identification (NADI) shared task. In addition to the system description, we give some details of the dialect identification experiments we conducted while preparing our submissions. In the end, we submitted only one official run. We used a Naive Bayes-based language identifier with character n-grams from one to four, of which we implemented a new version, which automatically optimizes its parameters. We also experimented with clustering the training data according to different topics. With the macro F1 score of 0.1963 on test set A and 0.1058 on test set B, we achieved the 18th position out of the 19 competing teams.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jauhiainen-etal-2022-optimizing">
<titleInfo>
<title>Optimizing Naive Bayes for Arabic Dialect Identification</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">Krister</namePart>
<namePart type="family">Lindén</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the language identification system used by the SUKI team in the 2022 Nuanced Arabic Dialect Identification (NADI) shared task. In addition to the system description, we give some details of the dialect identification experiments we conducted while preparing our submissions. In the end, we submitted only one official run. We used a Naive Bayes-based language identifier with character n-grams from one to four, of which we implemented a new version, which automatically optimizes its parameters. We also experimented with clustering the training data according to different topics. With the macro F1 score of 0.1963 on test set A and 0.1058 on test set B, we achieved the 18th position out of the 19 competing teams.</abstract>
<identifier type="citekey">jauhiainen-etal-2022-optimizing</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.40</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.40</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>409</start>
<end>414</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimizing Naive Bayes for Arabic Dialect Identification
%A Jauhiainen, Tommi
%A Jauhiainen, Heidi
%A Lindén, Krister
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F jauhiainen-etal-2022-optimizing
%X This article describes the language identification system used by the SUKI team in the 2022 Nuanced Arabic Dialect Identification (NADI) shared task. In addition to the system description, we give some details of the dialect identification experiments we conducted while preparing our submissions. In the end, we submitted only one official run. We used a Naive Bayes-based language identifier with character n-grams from one to four, of which we implemented a new version, which automatically optimizes its parameters. We also experimented with clustering the training data according to different topics. With the macro F1 score of 0.1963 on test set A and 0.1058 on test set B, we achieved the 18th position out of the 19 competing teams.
%R 10.18653/v1/2022.wanlp-1.40
%U https://aclanthology.org/2022.wanlp-1.40
%U https://doi.org/10.18653/v1/2022.wanlp-1.40
%P 409-414
Markdown (Informal)
[Optimizing Naive Bayes for Arabic Dialect Identification](https://aclanthology.org/2022.wanlp-1.40) (Jauhiainen et al., WANLP 2022)
ACL
- Tommi Jauhiainen, Heidi Jauhiainen, and Krister Lindén. 2022. Optimizing Naive Bayes for Arabic Dialect Identification. In Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), pages 409–414, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.