@inproceedings{kanjirangat-etal-2022-nlp,
title = "{NLP} {DI} at {NADI} Shared Task Subtask-1: Sub-word Level Convolutional Neural Models and Pre-trained Binary Classifiers for Dialect Identification",
author = "Kanjirangat, Vani and
Samardzic, Tanja and
Dolamic, Ljiljana and
Rinaldi, Fabio",
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-1.51",
doi = "10.18653/v1/2022.wanlp-1.51",
pages = "468--473",
abstract = "In this paper, we describe our systems submitted to the NADI Subtask 1: country-wise dialect classifications. We designed two types of solutions. The first type is convolutional neural network CNN) classifiers trained on subword segments of optimized lengths. The second type is fine-tuned classifiers with BERT-based language specific pre-trained models. To deal with the missing dialects in one of the test sets, we experimented with binary classifiers, analyzing the predicted probability distribution patterns and comparing them with the development set patterns. The better performing approach on the development set was fine-tuning language specific pre-trained model (best F-score 26.59{\%}). On the test set, on the other hand, we obtained the best performance with the CNN model trained on subword tokens obtained with a Unigram model (the best F-score 26.12{\%}). Re-training models on samples of training data simulating missing dialects gave the maximum performance on the test set version with a number of dialects lesser than the training set (F-score 16.44{\%})",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kanjirangat-etal-2022-nlp">
<titleInfo>
<title>NLP DI at NADI Shared Task Subtask-1: Sub-word Level Convolutional Neural Models and Pre-trained Binary Classifiers for Dialect Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vani</namePart>
<namePart type="family">Kanjirangat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanja</namePart>
<namePart type="family">Samardzic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ljiljana</namePart>
<namePart type="family">Dolamic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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>In this paper, we describe our systems submitted to the NADI Subtask 1: country-wise dialect classifications. We designed two types of solutions. The first type is convolutional neural network CNN) classifiers trained on subword segments of optimized lengths. The second type is fine-tuned classifiers with BERT-based language specific pre-trained models. To deal with the missing dialects in one of the test sets, we experimented with binary classifiers, analyzing the predicted probability distribution patterns and comparing them with the development set patterns. The better performing approach on the development set was fine-tuning language specific pre-trained model (best F-score 26.59%). On the test set, on the other hand, we obtained the best performance with the CNN model trained on subword tokens obtained with a Unigram model (the best F-score 26.12%). Re-training models on samples of training data simulating missing dialects gave the maximum performance on the test set version with a number of dialects lesser than the training set (F-score 16.44%)</abstract>
<identifier type="citekey">kanjirangat-etal-2022-nlp</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.51</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.51</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>468</start>
<end>473</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP DI at NADI Shared Task Subtask-1: Sub-word Level Convolutional Neural Models and Pre-trained Binary Classifiers for Dialect Identification
%A Kanjirangat, Vani
%A Samardzic, Tanja
%A Dolamic, Ljiljana
%A Rinaldi, Fabio
%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 kanjirangat-etal-2022-nlp
%X In this paper, we describe our systems submitted to the NADI Subtask 1: country-wise dialect classifications. We designed two types of solutions. The first type is convolutional neural network CNN) classifiers trained on subword segments of optimized lengths. The second type is fine-tuned classifiers with BERT-based language specific pre-trained models. To deal with the missing dialects in one of the test sets, we experimented with binary classifiers, analyzing the predicted probability distribution patterns and comparing them with the development set patterns. The better performing approach on the development set was fine-tuning language specific pre-trained model (best F-score 26.59%). On the test set, on the other hand, we obtained the best performance with the CNN model trained on subword tokens obtained with a Unigram model (the best F-score 26.12%). Re-training models on samples of training data simulating missing dialects gave the maximum performance on the test set version with a number of dialects lesser than the training set (F-score 16.44%)
%R 10.18653/v1/2022.wanlp-1.51
%U https://aclanthology.org/2022.wanlp-1.51
%U https://doi.org/10.18653/v1/2022.wanlp-1.51
%P 468-473
Markdown (Informal)
[NLP DI at NADI Shared Task Subtask-1: Sub-word Level Convolutional Neural Models and Pre-trained Binary Classifiers for Dialect Identification](https://aclanthology.org/2022.wanlp-1.51) (Kanjirangat et al., WANLP 2022)
ACL