@inproceedings{el-mekki-etal-2021-domain,
title = "Domain Adaptation for {A}rabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding",
author = "El Mekki, Abdellah and
El Mahdaouy, Abdelkader and
Berrada, Ismail and
Khoumsi, Ahmed",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.226",
doi = "10.18653/v1/2021.naacl-main.226",
pages = "2824--2837",
abstract = "Finetuning deep pre-trained language models has shown state-of-the-art performances on a wide range of Natural Language Processing (NLP) applications. Nevertheless, their generalization performance drops under domain shift. In the case of Arabic language, diglossia makes building and annotating corpora for each dialect and/or domain a more challenging task. Unsupervised Domain Adaptation tackles this issue by transferring the learned knowledge from labeled source domain data to unlabeled target domain data. In this paper, we propose a new unsupervised domain adaptation method for Arabic cross-domain and cross-dialect sentiment analysis from Contextualized Word Embedding. Several experiments are performed adopting the coarse-grained and the fine-grained taxonomies of Arabic dialects. The obtained results show that our method yields very promising results and outperforms several domain adaptation methods for most of the evaluated datasets. On average, our method increases the performance by an improvement rate of 20.8{\%} over the zero-shot transfer learning from BERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="el-mekki-etal-2021-domain">
<titleInfo>
<title>Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelkader</namePart>
<namePart type="family">El Mahdaouy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ismail</namePart>
<namePart type="family">Berrada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Khoumsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Finetuning deep pre-trained language models has shown state-of-the-art performances on a wide range of Natural Language Processing (NLP) applications. Nevertheless, their generalization performance drops under domain shift. In the case of Arabic language, diglossia makes building and annotating corpora for each dialect and/or domain a more challenging task. Unsupervised Domain Adaptation tackles this issue by transferring the learned knowledge from labeled source domain data to unlabeled target domain data. In this paper, we propose a new unsupervised domain adaptation method for Arabic cross-domain and cross-dialect sentiment analysis from Contextualized Word Embedding. Several experiments are performed adopting the coarse-grained and the fine-grained taxonomies of Arabic dialects. The obtained results show that our method yields very promising results and outperforms several domain adaptation methods for most of the evaluated datasets. On average, our method increases the performance by an improvement rate of 20.8% over the zero-shot transfer learning from BERT.</abstract>
<identifier type="citekey">el-mekki-etal-2021-domain</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.226</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.226</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>2824</start>
<end>2837</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding
%A El Mekki, Abdellah
%A El Mahdaouy, Abdelkader
%A Berrada, Ismail
%A Khoumsi, Ahmed
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F el-mekki-etal-2021-domain
%X Finetuning deep pre-trained language models has shown state-of-the-art performances on a wide range of Natural Language Processing (NLP) applications. Nevertheless, their generalization performance drops under domain shift. In the case of Arabic language, diglossia makes building and annotating corpora for each dialect and/or domain a more challenging task. Unsupervised Domain Adaptation tackles this issue by transferring the learned knowledge from labeled source domain data to unlabeled target domain data. In this paper, we propose a new unsupervised domain adaptation method for Arabic cross-domain and cross-dialect sentiment analysis from Contextualized Word Embedding. Several experiments are performed adopting the coarse-grained and the fine-grained taxonomies of Arabic dialects. The obtained results show that our method yields very promising results and outperforms several domain adaptation methods for most of the evaluated datasets. On average, our method increases the performance by an improvement rate of 20.8% over the zero-shot transfer learning from BERT.
%R 10.18653/v1/2021.naacl-main.226
%U https://aclanthology.org/2021.naacl-main.226
%U https://doi.org/10.18653/v1/2021.naacl-main.226
%P 2824-2837
Markdown (Informal)
[Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word Embedding](https://aclanthology.org/2021.naacl-main.226) (El Mekki et al., NAACL 2021)
ACL