Open AccessMultilingual Machine Translation: Deep Analysis of Language-Specific Encoder-Decoders
Author(s) -
Carlos Escolano,
Marta R. Costa-jussà,
José A. R. Fonollosa
Publication year - 2022
Publication title -
journal of artificial intelligence research/the journal of artificial intelligence research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.79
H-Index - 123
eISSN - 1943-5037
pISSN - 1076-9757
DOI - 10.1613/jair.1.12699
Subject(s) - machine translation , computer science , encoder , modular design , translation (biology) , artificial intelligence , natural language processing , representation (politics) , programming language , example based machine translation , biochemistry , chemistry , politics , messenger rna , political science , law , gene , operating system
State-of-the-art multilingual machine translation relies on a shared encoder-decoder. In this paper, we propose an alternative approach based on language-specific encoder-decoders, which can be easily extended to new languages by learning their corresponding modules. To establish a common interlingua representation, we simultaneously train N initial languages. Our experiments show that the proposed approach improves over the shared encoder-decoder for the initial languages and when adding new languages, without the need to retrain the remaining modules. All in all, our work closes the gap between shared and language-specific encoder-decoders, advancing toward modular multilingual machine translation systems that can be flexibly extended in lifelong learning settings.