@inproceedings{saini-etal-2020-generating,
title = "Generating Fluent Translations from Disfluent Text Without Access to Fluent References: {IIT} {B}ombay@{IWSLT}2020",
author = "Saini, Nikhil and
Khatri, Jyotsana and
Jyothi, Preethi and
Bhattacharyya, Pushpak",
editor = {Federico, Marcello and
Waibel, Alex and
Knight, Kevin and
Nakamura, Satoshi and
Ney, Hermann and
Niehues, Jan and
St{\"u}ker, Sebastian and
Wu, Dekai and
Mariani, Joseph and
Yvon, Francois},
booktitle = "Proceedings of the 17th International Conference on Spoken Language Translation",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.iwslt-1.22",
doi = "10.18653/v1/2020.iwslt-1.22",
pages = "178--186",
abstract = "Machine translation systems perform reasonably well when the input is well-formed speech or text. Conversational speech is spontaneous and inherently consists of many disfluencies. Producing fluent translations of disfluent source text would typically require parallel disfluent to fluent training data. However, fluent translations of spontaneous speech are an additional resource that is tedious to obtain. This work describes the submission of IIT Bombay to the Conversational Speech Translation challenge at IWSLT 2020. We specifically tackle the problem of disfluency removal in disfluent-to-fluent text-to-text translation assuming no access to fluent references during training. Common patterns of disfluency are extracted from disfluent references and a noise induction model is used to simulate them starting from a clean monolingual corpus. This synthetically constructed dataset is then considered as a proxy for labeled data during training. We also make use of additional fluent text in the target language to help generate fluent translations. This work uses no fluent references during training and beats a baseline model by a margin of 4.21 and 3.11 BLEU points where the baseline uses disfluent and fluent references, respectively. Index Terms- disfluency removal, machine translation, noise induction, leveraging monolingual data, denoising for disfluency removal.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saini-etal-2020-generating">
<titleInfo>
<title>Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Saini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyotsana</namePart>
<namePart type="family">Khatri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Conference on Spoken Language Translation</title>
</titleInfo>
<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">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dekai</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francois</namePart>
<namePart type="family">Yvon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation systems perform reasonably well when the input is well-formed speech or text. Conversational speech is spontaneous and inherently consists of many disfluencies. Producing fluent translations of disfluent source text would typically require parallel disfluent to fluent training data. However, fluent translations of spontaneous speech are an additional resource that is tedious to obtain. This work describes the submission of IIT Bombay to the Conversational Speech Translation challenge at IWSLT 2020. We specifically tackle the problem of disfluency removal in disfluent-to-fluent text-to-text translation assuming no access to fluent references during training. Common patterns of disfluency are extracted from disfluent references and a noise induction model is used to simulate them starting from a clean monolingual corpus. This synthetically constructed dataset is then considered as a proxy for labeled data during training. We also make use of additional fluent text in the target language to help generate fluent translations. This work uses no fluent references during training and beats a baseline model by a margin of 4.21 and 3.11 BLEU points where the baseline uses disfluent and fluent references, respectively. Index Terms- disfluency removal, machine translation, noise induction, leveraging monolingual data, denoising for disfluency removal.</abstract>
<identifier type="citekey">saini-etal-2020-generating</identifier>
<identifier type="doi">10.18653/v1/2020.iwslt-1.22</identifier>
<location>
<url>https://aclanthology.org/2020.iwslt-1.22</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>178</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020
%A Saini, Nikhil
%A Khatri, Jyotsana
%A Jyothi, Preethi
%A Bhattacharyya, Pushpak
%Y Federico, Marcello
%Y Waibel, Alex
%Y Knight, Kevin
%Y Nakamura, Satoshi
%Y Ney, Hermann
%Y Niehues, Jan
%Y Stüker, Sebastian
%Y Wu, Dekai
%Y Mariani, Joseph
%Y Yvon, Francois
%S Proceedings of the 17th International Conference on Spoken Language Translation
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F saini-etal-2020-generating
%X Machine translation systems perform reasonably well when the input is well-formed speech or text. Conversational speech is spontaneous and inherently consists of many disfluencies. Producing fluent translations of disfluent source text would typically require parallel disfluent to fluent training data. However, fluent translations of spontaneous speech are an additional resource that is tedious to obtain. This work describes the submission of IIT Bombay to the Conversational Speech Translation challenge at IWSLT 2020. We specifically tackle the problem of disfluency removal in disfluent-to-fluent text-to-text translation assuming no access to fluent references during training. Common patterns of disfluency are extracted from disfluent references and a noise induction model is used to simulate them starting from a clean monolingual corpus. This synthetically constructed dataset is then considered as a proxy for labeled data during training. We also make use of additional fluent text in the target language to help generate fluent translations. This work uses no fluent references during training and beats a baseline model by a margin of 4.21 and 3.11 BLEU points where the baseline uses disfluent and fluent references, respectively. Index Terms- disfluency removal, machine translation, noise induction, leveraging monolingual data, denoising for disfluency removal.
%R 10.18653/v1/2020.iwslt-1.22
%U https://aclanthology.org/2020.iwslt-1.22
%U https://doi.org/10.18653/v1/2020.iwslt-1.22
%P 178-186
Markdown (Informal)
[Generating Fluent Translations from Disfluent Text Without Access to Fluent References: IIT Bombay@IWSLT2020](https://aclanthology.org/2020.iwslt-1.22) (Saini et al., IWSLT 2020)
ACL