@inproceedings{ko-etal-2023-tagged,
title = "Tagged End-to-End Simultaneous Speech Translation Training Using Simultaneous Interpretation Data",
author = "Ko, Yuka and
Fukuda, Ryo and
Nishikawa, Yuta and
Kano, Yasumasa and
Sudoh, Katsuhito and
Nakamura, Satoshi",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.34",
doi = "10.18653/v1/2023.iwslt-1.34",
pages = "363--375",
abstract = "Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such as English and Japanese. A prospective approach to this problem is to mimic simultaneous interpretation (SI) using SI data to train a SimulST model. However, the size of such SI data is limited, so the SI data should be used together with ordinary bilingual data whose translations are given in offline. In this paper, we propose an effective way to train a SimulST model using mixed data of SI and offline. The proposed method trains a single model using the mixed data with style tags that tell the model to generate SI- or offline-style outputs. Experiment results show improvements of BLEURT in different latency ranges, and our analyses revealed the proposed model generates SI-style outputs more than the baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ko-etal-2023-tagged">
<titleInfo>
<title>Tagged End-to-End Simultaneous Speech Translation Training Using Simultaneous Interpretation Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuka</namePart>
<namePart type="family">Ko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Fukuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuta</namePart>
<namePart type="family">Nishikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasumasa</namePart>
<namePart type="family">Kano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such as English and Japanese. A prospective approach to this problem is to mimic simultaneous interpretation (SI) using SI data to train a SimulST model. However, the size of such SI data is limited, so the SI data should be used together with ordinary bilingual data whose translations are given in offline. In this paper, we propose an effective way to train a SimulST model using mixed data of SI and offline. The proposed method trains a single model using the mixed data with style tags that tell the model to generate SI- or offline-style outputs. Experiment results show improvements of BLEURT in different latency ranges, and our analyses revealed the proposed model generates SI-style outputs more than the baseline.</abstract>
<identifier type="citekey">ko-etal-2023-tagged</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.34</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.34</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>363</start>
<end>375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tagged End-to-End Simultaneous Speech Translation Training Using Simultaneous Interpretation Data
%A Ko, Yuka
%A Fukuda, Ryo
%A Nishikawa, Yuta
%A Kano, Yasumasa
%A Sudoh, Katsuhito
%A Nakamura, Satoshi
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F ko-etal-2023-tagged
%X Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such as English and Japanese. A prospective approach to this problem is to mimic simultaneous interpretation (SI) using SI data to train a SimulST model. However, the size of such SI data is limited, so the SI data should be used together with ordinary bilingual data whose translations are given in offline. In this paper, we propose an effective way to train a SimulST model using mixed data of SI and offline. The proposed method trains a single model using the mixed data with style tags that tell the model to generate SI- or offline-style outputs. Experiment results show improvements of BLEURT in different latency ranges, and our analyses revealed the proposed model generates SI-style outputs more than the baseline.
%R 10.18653/v1/2023.iwslt-1.34
%U https://aclanthology.org/2023.iwslt-1.34
%U https://doi.org/10.18653/v1/2023.iwslt-1.34
%P 363-375
Markdown (Informal)
[Tagged End-to-End Simultaneous Speech Translation Training Using Simultaneous Interpretation Data](https://aclanthology.org/2023.iwslt-1.34) (Ko et al., IWSLT 2023)
ACL