@inproceedings{sen-etal-2023-self,
title = "Self-training Reduces Flicker in Retranslation-based Simultaneous Translation",
author = "Sen, Sukanta and
Sennrich, Rico and
Zhang, Biao and
Haddow, Barry",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.270",
doi = "10.18653/v1/2023.eacl-main.270",
pages = "3734--3744",
abstract = "In simultaneous translation, the retranslation approach has the advantage of requiring no modifications to the inference engine. However, in order to reduce the undesirable flicker in the output, previous work has resorted to increasing the latency through masking, and introducing specialised inference, thus losing the simplicity of the approach. In this work, we show that self-training improves the flicker-latency tradeoff, while maintaining similar translation quality to the original. Our analysis indicates that self-training reduces flicker by controlling monotonicity. Furthermore, self-training can be combined with biased beam search to further improve the flicker-latency tradeoff.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sen-etal-2023-self">
<titleInfo>
<title>Self-training Reduces Flicker in Retranslation-based Simultaneous Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sukanta</namePart>
<namePart type="family">Sen</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>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</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 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</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>In simultaneous translation, the retranslation approach has the advantage of requiring no modifications to the inference engine. However, in order to reduce the undesirable flicker in the output, previous work has resorted to increasing the latency through masking, and introducing specialised inference, thus losing the simplicity of the approach. In this work, we show that self-training improves the flicker-latency tradeoff, while maintaining similar translation quality to the original. Our analysis indicates that self-training reduces flicker by controlling monotonicity. Furthermore, self-training can be combined with biased beam search to further improve the flicker-latency tradeoff.</abstract>
<identifier type="citekey">sen-etal-2023-self</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.270</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.270</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>3734</start>
<end>3744</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-training Reduces Flicker in Retranslation-based Simultaneous Translation
%A Sen, Sukanta
%A Sennrich, Rico
%A Zhang, Biao
%A Haddow, Barry
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F sen-etal-2023-self
%X In simultaneous translation, the retranslation approach has the advantage of requiring no modifications to the inference engine. However, in order to reduce the undesirable flicker in the output, previous work has resorted to increasing the latency through masking, and introducing specialised inference, thus losing the simplicity of the approach. In this work, we show that self-training improves the flicker-latency tradeoff, while maintaining similar translation quality to the original. Our analysis indicates that self-training reduces flicker by controlling monotonicity. Furthermore, self-training can be combined with biased beam search to further improve the flicker-latency tradeoff.
%R 10.18653/v1/2023.eacl-main.270
%U https://aclanthology.org/2023.eacl-main.270
%U https://doi.org/10.18653/v1/2023.eacl-main.270
%P 3734-3744
Markdown (Informal)
[Self-training Reduces Flicker in Retranslation-based Simultaneous Translation](https://aclanthology.org/2023.eacl-main.270) (Sen et al., EACL 2023)
ACL