@inproceedings{chen-etal-2021-improving-simultaneous,
title = "Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings",
author = "Chen, Junkun and
Zheng, Renjie and
Kita, Atsuhito and
Ma, Mingbo and
Huang, Liang",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.473/",
doi = "10.18653/v1/2021.emnlp-main.473",
pages = "5857--5864",
abstract = "Simultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay. However, due to the lack of large-scale, high-quality simultaneous translation datasets, most such systems are still trained on conventional full-sentence bitexts. This is far from ideal for the simultaneous scenario due to the abundance of unnecessary long-distance reorderings in those bitexts. We propose a novel method that rewrites the target side of existing full-sentence corpora into simultaneous-style translation. Experiments on Zh$\rightarrow$En and Ja$\rightarrow$En simultaneous translation show substantial improvements (up to +2.7 BLEU) with the addition of these generated pseudo-references."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2021-improving-simultaneous">
<titleInfo>
<title>Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junkun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renjie</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuhito</namePart>
<namePart type="family">Kita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingbo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Simultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay. However, due to the lack of large-scale, high-quality simultaneous translation datasets, most such systems are still trained on conventional full-sentence bitexts. This is far from ideal for the simultaneous scenario due to the abundance of unnecessary long-distance reorderings in those bitexts. We propose a novel method that rewrites the target side of existing full-sentence corpora into simultaneous-style translation. Experiments on Zh\rightarrowEn and Ja\rightarrowEn simultaneous translation show substantial improvements (up to +2.7 BLEU) with the addition of these generated pseudo-references.</abstract>
<identifier type="citekey">chen-etal-2021-improving-simultaneous</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.473</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.473/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>5857</start>
<end>5864</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings
%A Chen, Junkun
%A Zheng, Renjie
%A Kita, Atsuhito
%A Ma, Mingbo
%A Huang, Liang
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F chen-etal-2021-improving-simultaneous
%X Simultaneous translation is vastly different from full-sentence translation, in the sense that it starts translation before the source sentence ends, with only a few words delay. However, due to the lack of large-scale, high-quality simultaneous translation datasets, most such systems are still trained on conventional full-sentence bitexts. This is far from ideal for the simultaneous scenario due to the abundance of unnecessary long-distance reorderings in those bitexts. We propose a novel method that rewrites the target side of existing full-sentence corpora into simultaneous-style translation. Experiments on Zh\rightarrowEn and Ja\rightarrowEn simultaneous translation show substantial improvements (up to +2.7 BLEU) with the addition of these generated pseudo-references.
%R 10.18653/v1/2021.emnlp-main.473
%U https://aclanthology.org/2021.emnlp-main.473/
%U https://doi.org/10.18653/v1/2021.emnlp-main.473
%P 5857-5864
Markdown (Informal)
[Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings](https://aclanthology.org/2021.emnlp-main.473/) (Chen et al., EMNLP 2021)
ACL