@inproceedings{wicks-duh-2022-effects,
title = "The Effects of Language Token Prefixing for Multilingual Machine Translation",
author = "Wicks, Rachel and
Duh, Kevin",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.19/",
doi = "10.18653/v1/2022.aacl-short.19",
pages = "148--153",
abstract = "Machine translation traditionally refers to translating from a single source language into a single target language. In recent years, the field has moved towards large neural models either translating from or into many languages. The model must be correctly cued to translate into the correct target language. This is typically done by prefixing language tokens onto the source or target sequence. The location and content of the prefix can vary and many use different approaches without much justification towards one approach or another. As a guidance to future researchers and directions for future work, we present a series of experiments that show how the positioning and type of a target language prefix token effects translation performance. We show that source side prefixes improve performance. Further, we find that the best language information to denote via tokens depends on the supported language set."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wicks-duh-2022-effects">
<titleInfo>
<title>The Effects of Language Token Prefixing for Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Wicks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<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">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</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>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation traditionally refers to translating from a single source language into a single target language. In recent years, the field has moved towards large neural models either translating from or into many languages. The model must be correctly cued to translate into the correct target language. This is typically done by prefixing language tokens onto the source or target sequence. The location and content of the prefix can vary and many use different approaches without much justification towards one approach or another. As a guidance to future researchers and directions for future work, we present a series of experiments that show how the positioning and type of a target language prefix token effects translation performance. We show that source side prefixes improve performance. Further, we find that the best language information to denote via tokens depends on the supported language set.</abstract>
<identifier type="citekey">wicks-duh-2022-effects</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-short.19</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.19/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>148</start>
<end>153</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Effects of Language Token Prefixing for Multilingual Machine Translation
%A Wicks, Rachel
%A Duh, Kevin
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F wicks-duh-2022-effects
%X Machine translation traditionally refers to translating from a single source language into a single target language. In recent years, the field has moved towards large neural models either translating from or into many languages. The model must be correctly cued to translate into the correct target language. This is typically done by prefixing language tokens onto the source or target sequence. The location and content of the prefix can vary and many use different approaches without much justification towards one approach or another. As a guidance to future researchers and directions for future work, we present a series of experiments that show how the positioning and type of a target language prefix token effects translation performance. We show that source side prefixes improve performance. Further, we find that the best language information to denote via tokens depends on the supported language set.
%R 10.18653/v1/2022.aacl-short.19
%U https://aclanthology.org/2022.aacl-short.19/
%U https://doi.org/10.18653/v1/2022.aacl-short.19
%P 148-153
Markdown (Informal)
[The Effects of Language Token Prefixing for Multilingual Machine Translation](https://aclanthology.org/2022.aacl-short.19/) (Wicks & Duh, AACL-IJCNLP 2022)
ACL
- Rachel Wicks and Kevin Duh. 2022. The Effects of Language Token Prefixing for Multilingual Machine Translation. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 148–153, Online only. Association for Computational Linguistics.