@inproceedings{gupta-etal-2022-pre,
title = "Pre-training Synthetic Cross-lingual Decoder for Multilingual Samples Adaptation in {E}-Commerce Neural Machine Translation",
author = "Gupta, Kamal Kumar and
Chennabasavraj, Soumya and
Garera, Nikesh and
Ekbal, Asif",
editor = {Moniz, Helena and
Macken, Lieve and
Rufener, Andrew and
Barrault, Lo{\"i}c and
Costa-juss{\`a}, Marta R. and
Declercq, Christophe and
Koponen, Maarit and
Kemp, Ellie and
Pilos, Spyridon and
Forcada, Mikel L. and
Scarton, Carolina and
Van den Bogaert, Joachim and
Daems, Joke and
Tezcan, Arda and
Vanroy, Bram and
Fonteyne, Margot},
booktitle = "Proceedings of the 23rd Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2022",
address = "Ghent, Belgium",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2022.eamt-1.27/",
pages = "241--248",
abstract = "Availability of the user reviews in vernacular languages is helpful for the users to get information regarding the products. Since most of the e-commerce websites allow the reviews in English language only, it is important to provide the translated versions of the reviews to the non-English speaking users. Translation of the user reviews from English to vernacular languages is a challenging task, predominantly due to the lack of sufficient in-domain datasets. In this paper, we present a pre-training based efficient technique which is used to adapt and improve the single multilingual neural machine translation (NMT) model for the low-resource language pairs. The pre-trained model contains a special synthetic cross-lingual decoder. The decoder for the pre-training is trained over the cross-lingual target samples where the phrases are replaced with their translated counterparts. After pre-training, the model is adapted to multiple samples of the low-resource language pairs using incremental learning that does not require full training from the very scratch. We perform the experiments over eight low-resource and three high resource language pairs from the generic domain, and two language pairs from the product review domains. Through our synthetic multilingual decoder based pre-training, we achieve improvements of upto 4.35 BLEU points compared to the baseline and 2.13 BLEU points compared to the previous code-switched pre-trained models. The review domain outputs from the proposed model are evaluated in real time by human evaluators in the e-commerce company Flipkart."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2022-pre">
<titleInfo>
<title>Pre-training Synthetic Cross-lingual Decoder for Multilingual Samples Adaptation in E-Commerce Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamal</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumya</namePart>
<namePart type="family">Chennabasavraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikesh</namePart>
<namePart type="family">Garera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lieve</namePart>
<namePart type="family">Macken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Rufener</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Declercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellie</namePart>
<namePart type="family">Kemp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spyridon</namePart>
<namePart type="family">Pilos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Tezcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bram</namePart>
<namePart type="family">Vanroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Fonteyne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Ghent, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Availability of the user reviews in vernacular languages is helpful for the users to get information regarding the products. Since most of the e-commerce websites allow the reviews in English language only, it is important to provide the translated versions of the reviews to the non-English speaking users. Translation of the user reviews from English to vernacular languages is a challenging task, predominantly due to the lack of sufficient in-domain datasets. In this paper, we present a pre-training based efficient technique which is used to adapt and improve the single multilingual neural machine translation (NMT) model for the low-resource language pairs. The pre-trained model contains a special synthetic cross-lingual decoder. The decoder for the pre-training is trained over the cross-lingual target samples where the phrases are replaced with their translated counterparts. After pre-training, the model is adapted to multiple samples of the low-resource language pairs using incremental learning that does not require full training from the very scratch. We perform the experiments over eight low-resource and three high resource language pairs from the generic domain, and two language pairs from the product review domains. Through our synthetic multilingual decoder based pre-training, we achieve improvements of upto 4.35 BLEU points compared to the baseline and 2.13 BLEU points compared to the previous code-switched pre-trained models. The review domain outputs from the proposed model are evaluated in real time by human evaluators in the e-commerce company Flipkart.</abstract>
<identifier type="citekey">gupta-etal-2022-pre</identifier>
<location>
<url>https://aclanthology.org/2022.eamt-1.27/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>241</start>
<end>248</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-training Synthetic Cross-lingual Decoder for Multilingual Samples Adaptation in E-Commerce Neural Machine Translation
%A Gupta, Kamal Kumar
%A Chennabasavraj, Soumya
%A Garera, Nikesh
%A Ekbal, Asif
%Y Moniz, Helena
%Y Macken, Lieve
%Y Rufener, Andrew
%Y Barrault, Loïc
%Y Costa-jussà, Marta R.
%Y Declercq, Christophe
%Y Koponen, Maarit
%Y Kemp, Ellie
%Y Pilos, Spyridon
%Y Forcada, Mikel L.
%Y Scarton, Carolina
%Y Van den Bogaert, Joachim
%Y Daems, Joke
%Y Tezcan, Arda
%Y Vanroy, Bram
%Y Fonteyne, Margot
%S Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
%D 2022
%8 June
%I European Association for Machine Translation
%C Ghent, Belgium
%F gupta-etal-2022-pre
%X Availability of the user reviews in vernacular languages is helpful for the users to get information regarding the products. Since most of the e-commerce websites allow the reviews in English language only, it is important to provide the translated versions of the reviews to the non-English speaking users. Translation of the user reviews from English to vernacular languages is a challenging task, predominantly due to the lack of sufficient in-domain datasets. In this paper, we present a pre-training based efficient technique which is used to adapt and improve the single multilingual neural machine translation (NMT) model for the low-resource language pairs. The pre-trained model contains a special synthetic cross-lingual decoder. The decoder for the pre-training is trained over the cross-lingual target samples where the phrases are replaced with their translated counterparts. After pre-training, the model is adapted to multiple samples of the low-resource language pairs using incremental learning that does not require full training from the very scratch. We perform the experiments over eight low-resource and three high resource language pairs from the generic domain, and two language pairs from the product review domains. Through our synthetic multilingual decoder based pre-training, we achieve improvements of upto 4.35 BLEU points compared to the baseline and 2.13 BLEU points compared to the previous code-switched pre-trained models. The review domain outputs from the proposed model are evaluated in real time by human evaluators in the e-commerce company Flipkart.
%U https://aclanthology.org/2022.eamt-1.27/
%P 241-248
Markdown (Informal)
[Pre-training Synthetic Cross-lingual Decoder for Multilingual Samples Adaptation in E-Commerce Neural Machine Translation](https://aclanthology.org/2022.eamt-1.27/) (Gupta et al., EAMT 2022)
ACL