@inproceedings{amrhein-sennrich-2020-romanization,
title = "On {R}omanization for Model Transfer Between Scripts in Neural Machine Translation",
author = "Amrhein, Chantal and
Sennrich, Rico",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.223",
doi = "10.18653/v1/2020.findings-emnlp.223",
pages = "2461--2469",
abstract = "Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amrhein-sennrich-2020-romanization">
<titleInfo>
<title>On Romanization for Model Transfer Between Scripts in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chantal</namePart>
<namePart type="family">Amrhein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.</abstract>
<identifier type="citekey">amrhein-sennrich-2020-romanization</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.223</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.223</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2461</start>
<end>2469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On Romanization for Model Transfer Between Scripts in Neural Machine Translation
%A Amrhein, Chantal
%A Sennrich, Rico
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F amrhein-sennrich-2020-romanization
%X Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.
%R 10.18653/v1/2020.findings-emnlp.223
%U https://aclanthology.org/2020.findings-emnlp.223
%U https://doi.org/10.18653/v1/2020.findings-emnlp.223
%P 2461-2469
Markdown (Informal)
[On Romanization for Model Transfer Between Scripts in Neural Machine Translation](https://aclanthology.org/2020.findings-emnlp.223) (Amrhein & Sennrich, Findings 2020)
ACL