@inproceedings{deb-etal-2021-conditional-generative,
title = "A Conditional Generative Matching Model for Multi-lingual Reply Suggestion",
author = "Deb, Budhaditya and
Zheng, Guoqing and
Shokouhi, Milad and
Awadallah, Ahmed Hassan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.134",
doi = "10.18653/v1/2021.findings-emnlp.134",
pages = "1553--1568",
abstract = "We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multilingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multilingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multilingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10{\%} on average, and 16{\%}for low resource languages. CGM also shows remarkable improvements in diversity (80{\%}) illustrating its expressiveness in representation of multi-lingual data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deb-etal-2021-conditional-generative">
<titleInfo>
<title>A Conditional Generative Matching Model for Multi-lingual Reply Suggestion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Budhaditya</namePart>
<namePart type="family">Deb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoqing</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milad</namePart>
<namePart type="family">Shokouhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">Hassan</namePart>
<namePart type="family">Awadallah</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>Findings of the Association for Computational Linguistics: EMNLP 2021</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">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multilingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multilingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multilingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10% on average, and 16%for low resource languages. CGM also shows remarkable improvements in diversity (80%) illustrating its expressiveness in representation of multi-lingual data.</abstract>
<identifier type="citekey">deb-etal-2021-conditional-generative</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.134</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.134</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1553</start>
<end>1568</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Conditional Generative Matching Model for Multi-lingual Reply Suggestion
%A Deb, Budhaditya
%A Zheng, Guoqing
%A Shokouhi, Milad
%A Awadallah, Ahmed Hassan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F deb-etal-2021-conditional-generative
%X We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously. Multilingual models are often challenged by model capacity and severe data distribution skew across languages. While prior works largely focus on monolingual models, we propose Conditional Generative Matching models (CGM), optimized within a Variational Autoencoder framework to address challenges arising from multilingual RS. CGM does so with expressive message conditional priors, mixture densities to enhance multilingual data representation, latent alignment for language discrimination, and effective variational optimization techniques for training multilingual RS. The enhancements result in performance that exceed competitive baselines in relevance (ROUGE score) by more than 10% on average, and 16%for low resource languages. CGM also shows remarkable improvements in diversity (80%) illustrating its expressiveness in representation of multi-lingual data.
%R 10.18653/v1/2021.findings-emnlp.134
%U https://aclanthology.org/2021.findings-emnlp.134
%U https://doi.org/10.18653/v1/2021.findings-emnlp.134
%P 1553-1568
Markdown (Informal)
[A Conditional Generative Matching Model for Multi-lingual Reply Suggestion](https://aclanthology.org/2021.findings-emnlp.134) (Deb et al., Findings 2021)
ACL