@inproceedings{lee-etal-2023-quantifying,
title = "Quantifying Information of Tokens for Simple and Flexible Simultaneous Machine Translation",
author = "Lee, DongHyun and
Park, Minkyung and
Lee, Byung-Jun",
editor = "Jiang, Jing and
Reitter, David and
Deng, Shumin",
booktitle = "Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.conll-1.14",
doi = "10.18653/v1/2023.conll-1.14",
pages = "200--210",
abstract = "Simultaneous Translation (ST) involves translating with only partial source inputs instead of the entire source inputs, a process that can potentially result in translation quality degradation. Previous approaches to balancing translation quality and latency have demonstrated that it is more efficient and effective to leverage an offline model with a reasonable policy. However, using an offline model also leads to a distribution shift since it is not trained with partial source inputs, and it can be improved by training an additional module that informs us when to translate. In this paper, we propose an Information Quantifier (IQ) that models source and target information to determine whether the offline model has sufficient information for translation, trained with oracle action sequences generated from the offline model. IQ, by quantifying information, helps in formulating a suitable policy for Simultaneous Translation that better generalizes and also allows us to control the trade-off between quality and latency naturally. Experiments on various language pairs show that our proposed model outperforms baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2023-quantifying">
<titleInfo>
<title>Quantifying Information of Tokens for Simple and Flexible Simultaneous Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">DongHyun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minkyung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byung-Jun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Reitter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shumin</namePart>
<namePart type="family">Deng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Simultaneous Translation (ST) involves translating with only partial source inputs instead of the entire source inputs, a process that can potentially result in translation quality degradation. Previous approaches to balancing translation quality and latency have demonstrated that it is more efficient and effective to leverage an offline model with a reasonable policy. However, using an offline model also leads to a distribution shift since it is not trained with partial source inputs, and it can be improved by training an additional module that informs us when to translate. In this paper, we propose an Information Quantifier (IQ) that models source and target information to determine whether the offline model has sufficient information for translation, trained with oracle action sequences generated from the offline model. IQ, by quantifying information, helps in formulating a suitable policy for Simultaneous Translation that better generalizes and also allows us to control the trade-off between quality and latency naturally. Experiments on various language pairs show that our proposed model outperforms baselines.</abstract>
<identifier type="citekey">lee-etal-2023-quantifying</identifier>
<identifier type="doi">10.18653/v1/2023.conll-1.14</identifier>
<location>
<url>https://aclanthology.org/2023.conll-1.14</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>200</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quantifying Information of Tokens for Simple and Flexible Simultaneous Machine Translation
%A Lee, DongHyun
%A Park, Minkyung
%A Lee, Byung-Jun
%Y Jiang, Jing
%Y Reitter, David
%Y Deng, Shumin
%S Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lee-etal-2023-quantifying
%X Simultaneous Translation (ST) involves translating with only partial source inputs instead of the entire source inputs, a process that can potentially result in translation quality degradation. Previous approaches to balancing translation quality and latency have demonstrated that it is more efficient and effective to leverage an offline model with a reasonable policy. However, using an offline model also leads to a distribution shift since it is not trained with partial source inputs, and it can be improved by training an additional module that informs us when to translate. In this paper, we propose an Information Quantifier (IQ) that models source and target information to determine whether the offline model has sufficient information for translation, trained with oracle action sequences generated from the offline model. IQ, by quantifying information, helps in formulating a suitable policy for Simultaneous Translation that better generalizes and also allows us to control the trade-off between quality and latency naturally. Experiments on various language pairs show that our proposed model outperforms baselines.
%R 10.18653/v1/2023.conll-1.14
%U https://aclanthology.org/2023.conll-1.14
%U https://doi.org/10.18653/v1/2023.conll-1.14
%P 200-210
Markdown (Informal)
[Quantifying Information of Tokens for Simple and Flexible Simultaneous Machine Translation](https://aclanthology.org/2023.conll-1.14) (Lee et al., CoNLL 2023)
ACL