@inproceedings{tian-etal-2022-improving-english,
title = "Improving {E}nglish-{A}rabic Transliteration with Phonemic Memories",
author = "Tian, Yuanhe and
Lou, Renze and
Pang, Xiangyu and
Wang, Lianxi and
Jiang, Shengyi and
Song, Yan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.238/",
doi = "10.18653/v1/2022.findings-emnlp.238",
pages = "3262--3272",
abstract = "Transliteration is an important task in natural language processing (NLP) which aims to convert a name in the source language to the target language without changing its pronunciation. Particularly, transliteration from English to Arabic is highly needed in many applications, especially in countries (e.g., United Arab Emirates (UAE)) whose most citizens are foreigners but the official language is Arabic. In such a task-oriented scenario, namely transliterating the English names to the corresponding Arabic ones, the performance of the transliteration model is highly important. However, most existing neural approaches mainly apply a universal transliteration model with advanced encoders and decoders to the task, where limited attention is paid to leveraging the phonemic association between English and Arabic to further improve model performance. In this paper, we focus on transliteration of people`s names from English to Arabic for the general public. In doing so, we collect a corpus named EANames by extracting high quality name pairs from online resources which better represent the names in the general public than linked Wikipedia entries that are always names of famous people). We propose a model for English-Arabic transliteration, where a memory module modeling the phonemic association between English and Arabic is used to guide the transliteration process. We run experiments on the collected data and the results demonstrate the effectiveness of our approach for English-Arabic transliteration."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2022-improving-english">
<titleInfo>
<title>Improving English-Arabic Transliteration with Phonemic Memories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanhe</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renze</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Pang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianxi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengyi</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</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>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</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</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transliteration is an important task in natural language processing (NLP) which aims to convert a name in the source language to the target language without changing its pronunciation. Particularly, transliteration from English to Arabic is highly needed in many applications, especially in countries (e.g., United Arab Emirates (UAE)) whose most citizens are foreigners but the official language is Arabic. In such a task-oriented scenario, namely transliterating the English names to the corresponding Arabic ones, the performance of the transliteration model is highly important. However, most existing neural approaches mainly apply a universal transliteration model with advanced encoders and decoders to the task, where limited attention is paid to leveraging the phonemic association between English and Arabic to further improve model performance. In this paper, we focus on transliteration of people‘s names from English to Arabic for the general public. In doing so, we collect a corpus named EANames by extracting high quality name pairs from online resources which better represent the names in the general public than linked Wikipedia entries that are always names of famous people). We propose a model for English-Arabic transliteration, where a memory module modeling the phonemic association between English and Arabic is used to guide the transliteration process. We run experiments on the collected data and the results demonstrate the effectiveness of our approach for English-Arabic transliteration.</abstract>
<identifier type="citekey">tian-etal-2022-improving-english</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.238</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.238/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>3262</start>
<end>3272</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving English-Arabic Transliteration with Phonemic Memories
%A Tian, Yuanhe
%A Lou, Renze
%A Pang, Xiangyu
%A Wang, Lianxi
%A Jiang, Shengyi
%A Song, Yan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F tian-etal-2022-improving-english
%X Transliteration is an important task in natural language processing (NLP) which aims to convert a name in the source language to the target language without changing its pronunciation. Particularly, transliteration from English to Arabic is highly needed in many applications, especially in countries (e.g., United Arab Emirates (UAE)) whose most citizens are foreigners but the official language is Arabic. In such a task-oriented scenario, namely transliterating the English names to the corresponding Arabic ones, the performance of the transliteration model is highly important. However, most existing neural approaches mainly apply a universal transliteration model with advanced encoders and decoders to the task, where limited attention is paid to leveraging the phonemic association between English and Arabic to further improve model performance. In this paper, we focus on transliteration of people‘s names from English to Arabic for the general public. In doing so, we collect a corpus named EANames by extracting high quality name pairs from online resources which better represent the names in the general public than linked Wikipedia entries that are always names of famous people). We propose a model for English-Arabic transliteration, where a memory module modeling the phonemic association between English and Arabic is used to guide the transliteration process. We run experiments on the collected data and the results demonstrate the effectiveness of our approach for English-Arabic transliteration.
%R 10.18653/v1/2022.findings-emnlp.238
%U https://aclanthology.org/2022.findings-emnlp.238/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.238
%P 3262-3272
Markdown (Informal)
[Improving English-Arabic Transliteration with Phonemic Memories](https://aclanthology.org/2022.findings-emnlp.238/) (Tian et al., Findings 2022)
ACL
- Yuanhe Tian, Renze Lou, Xiangyu Pang, Lianxi Wang, Shengyi Jiang, and Yan Song. 2022. Improving English-Arabic Transliteration with Phonemic Memories. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3262–3272, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.