@inproceedings{hamed-etal-2023-investigating,
title = "Investigating Lexical Replacements for {A}rabic-{E}nglish Code-Switched Data Augmentation",
author = "Hamed, Injy and
Habash, Nizar and
Abdennadher, Slim and
Vu, Ngoc Thang",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.loresmt-1.7",
doi = "10.18653/v1/2023.loresmt-1.7",
pages = "86--100",
abstract = "Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements using word-aligned parallel corpora where CS points are either randomly chosen or learnt using a sequence-to-sequence model. We compare these approaches against dictionary-based replacements. We assess the quality of generated sentences through human evaluation and evaluate the effectiveness of data augmentation on machine translation (MT), automatic speech recognition (ASR), and speech translation (ST) tasks. Results show that using a predictive model results in more natural CS sentences compared to the random approach, as reported in human judgements. In the downstream tasks, despite the random approach generating more data, both approaches perform equally (outperforming dictionary-based replacements). Overall, data augmentation achieves 34{\%} improvement in perplexity, 5.2{\%} relative improvement on WER for ASR task, +4.0-5.1 BLEU points on MT task, and +2.1-2.2 BLEU points on ST over a baseline trained on available data without augmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamed-etal-2023-investigating">
<titleInfo>
<title>Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slim</namePart>
<namePart type="family">Abdennadher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc</namePart>
<namePart type="given">Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements using word-aligned parallel corpora where CS points are either randomly chosen or learnt using a sequence-to-sequence model. We compare these approaches against dictionary-based replacements. We assess the quality of generated sentences through human evaluation and evaluate the effectiveness of data augmentation on machine translation (MT), automatic speech recognition (ASR), and speech translation (ST) tasks. Results show that using a predictive model results in more natural CS sentences compared to the random approach, as reported in human judgements. In the downstream tasks, despite the random approach generating more data, both approaches perform equally (outperforming dictionary-based replacements). Overall, data augmentation achieves 34% improvement in perplexity, 5.2% relative improvement on WER for ASR task, +4.0-5.1 BLEU points on MT task, and +2.1-2.2 BLEU points on ST over a baseline trained on available data without augmentation.</abstract>
<identifier type="citekey">hamed-etal-2023-investigating</identifier>
<identifier type="doi">10.18653/v1/2023.loresmt-1.7</identifier>
<location>
<url>https://aclanthology.org/2023.loresmt-1.7</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>86</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation
%A Hamed, Injy
%A Habash, Nizar
%A Abdennadher, Slim
%A Vu, Ngoc Thang
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F hamed-etal-2023-investigating
%X Data sparsity is a main problem hindering the development of code-switching (CS) NLP systems. In this paper, we investigate data augmentation techniques for synthesizing dialectal Arabic-English CS text. We perform lexical replacements using word-aligned parallel corpora where CS points are either randomly chosen or learnt using a sequence-to-sequence model. We compare these approaches against dictionary-based replacements. We assess the quality of generated sentences through human evaluation and evaluate the effectiveness of data augmentation on machine translation (MT), automatic speech recognition (ASR), and speech translation (ST) tasks. Results show that using a predictive model results in more natural CS sentences compared to the random approach, as reported in human judgements. In the downstream tasks, despite the random approach generating more data, both approaches perform equally (outperforming dictionary-based replacements). Overall, data augmentation achieves 34% improvement in perplexity, 5.2% relative improvement on WER for ASR task, +4.0-5.1 BLEU points on MT task, and +2.1-2.2 BLEU points on ST over a baseline trained on available data without augmentation.
%R 10.18653/v1/2023.loresmt-1.7
%U https://aclanthology.org/2023.loresmt-1.7
%U https://doi.org/10.18653/v1/2023.loresmt-1.7
%P 86-100
Markdown (Informal)
[Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation](https://aclanthology.org/2023.loresmt-1.7) (Hamed et al., LoResMT 2023)
ACL