@inproceedings{xu-etal-2021-modeling,
title = "Modeling Task-Aware {MIMO} Cardinality for Efficient Multilingual Neural Machine Translation",
author = "Xu, Hongfei and
Liu, Qiuhui and
van Genabith, Josef and
Xiong, Deyi",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.46/",
doi = "10.18653/v1/2021.acl-short.46",
pages = "361--367",
abstract = "Neural machine translation has achieved great success in bilingual settings, as well as in multilingual settings. With the increase of the number of languages, multilingual systems tend to underperform their bilingual counterparts. Model capacity has been found crucial for massively multilingual NMT to support language pairs with varying typological characteristics. Previous work increases the modeling capacity by deepening or widening the Transformer. However, modeling cardinality based on aggregating a set of transformations with the same topology has been proven more effective than going deeper or wider when increasing capacity. In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality. Unlike previous work which feeds the same input to several transformations and merges their outputs into one, we present a Multi-Input-Multi-Output (MIMO) architecture that allows each transformation of the block to have its own input. We also present a task-aware attention mechanism to learn to selectively utilize individual transformations from a set of transformations for different translation directions. Our model surpasses previous work and establishes a new state-of-the-art on the large scale OPUS-100 corpus while being 1.31 times as fast."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2021-modeling">
<titleInfo>
<title>Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiuhui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Neural machine translation has achieved great success in bilingual settings, as well as in multilingual settings. With the increase of the number of languages, multilingual systems tend to underperform their bilingual counterparts. Model capacity has been found crucial for massively multilingual NMT to support language pairs with varying typological characteristics. Previous work increases the modeling capacity by deepening or widening the Transformer. However, modeling cardinality based on aggregating a set of transformations with the same topology has been proven more effective than going deeper or wider when increasing capacity. In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality. Unlike previous work which feeds the same input to several transformations and merges their outputs into one, we present a Multi-Input-Multi-Output (MIMO) architecture that allows each transformation of the block to have its own input. We also present a task-aware attention mechanism to learn to selectively utilize individual transformations from a set of transformations for different translation directions. Our model surpasses previous work and establishes a new state-of-the-art on the large scale OPUS-100 corpus while being 1.31 times as fast.</abstract>
<identifier type="citekey">xu-etal-2021-modeling</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.46</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.46/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>361</start>
<end>367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation
%A Xu, Hongfei
%A Liu, Qiuhui
%A van Genabith, Josef
%A Xiong, Deyi
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F xu-etal-2021-modeling
%X Neural machine translation has achieved great success in bilingual settings, as well as in multilingual settings. With the increase of the number of languages, multilingual systems tend to underperform their bilingual counterparts. Model capacity has been found crucial for massively multilingual NMT to support language pairs with varying typological characteristics. Previous work increases the modeling capacity by deepening or widening the Transformer. However, modeling cardinality based on aggregating a set of transformations with the same topology has been proven more effective than going deeper or wider when increasing capacity. In this paper, we propose to efficiently increase the capacity for multilingual NMT by increasing the cardinality. Unlike previous work which feeds the same input to several transformations and merges their outputs into one, we present a Multi-Input-Multi-Output (MIMO) architecture that allows each transformation of the block to have its own input. We also present a task-aware attention mechanism to learn to selectively utilize individual transformations from a set of transformations for different translation directions. Our model surpasses previous work and establishes a new state-of-the-art on the large scale OPUS-100 corpus while being 1.31 times as fast.
%R 10.18653/v1/2021.acl-short.46
%U https://aclanthology.org/2021.acl-short.46/
%U https://doi.org/10.18653/v1/2021.acl-short.46
%P 361-367
Markdown (Informal)
[Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation](https://aclanthology.org/2021.acl-short.46/) (Xu et al., ACL-IJCNLP 2021)
ACL