@inproceedings{rikters-nakazawa-2024-revisiting,
title = "Revisiting Context Choices for Context-aware Machine Translation",
author = "Rikters, Matiss and
Nakazawa, Toshiaki",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1226",
pages = "14073--14079",
abstract = "One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models actually learn useful signals from the context or are improvements in automatic evaluation metrics just a side-effect. We show that multi-source transformer models improve MT over standard transformer-base models even with empty lines provided as context, but the translation quality improves significantly (1.51 - 2.65 BLEU) when a sufficient amount of correct context is provided. We also show that even though randomly shuffling in-domain context can also improve over baselines, the correct context further improves translation quality and random out-of-domain context further degrades it.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rikters-nakazawa-2024-revisiting">
<titleInfo>
<title>Revisiting Context Choices for Context-aware Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matiss</namePart>
<namePart type="family">Rikters</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models actually learn useful signals from the context or are improvements in automatic evaluation metrics just a side-effect. We show that multi-source transformer models improve MT over standard transformer-base models even with empty lines provided as context, but the translation quality improves significantly (1.51 - 2.65 BLEU) when a sufficient amount of correct context is provided. We also show that even though randomly shuffling in-domain context can also improve over baselines, the correct context further improves translation quality and random out-of-domain context further degrades it.</abstract>
<identifier type="citekey">rikters-nakazawa-2024-revisiting</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1226</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14073</start>
<end>14079</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Context Choices for Context-aware Machine Translation
%A Rikters, Matiss
%A Nakazawa, Toshiaki
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F rikters-nakazawa-2024-revisiting
%X One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models actually learn useful signals from the context or are improvements in automatic evaluation metrics just a side-effect. We show that multi-source transformer models improve MT over standard transformer-base models even with empty lines provided as context, but the translation quality improves significantly (1.51 - 2.65 BLEU) when a sufficient amount of correct context is provided. We also show that even though randomly shuffling in-domain context can also improve over baselines, the correct context further improves translation quality and random out-of-domain context further degrades it.
%U https://aclanthology.org/2024.lrec-main.1226
%P 14073-14079
Markdown (Informal)
[Revisiting Context Choices for Context-aware Machine Translation](https://aclanthology.org/2024.lrec-main.1226) (Rikters & Nakazawa, LREC-COLING 2024)
ACL