Multilingual Machine Translation: Deep Analysis of Language-Specific Encoder-Decoders

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 interlingu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The Journal of artificial intelligence research Ročník 73; s. 1535 - 1552
Hlavní autoři: Escolano, Carlos, Ruiz Costa-jussà, Marta, R. Fonollosa, José A.
Médium: Journal Article
Jazyk:angličtina
Vydáno: San Francisco AI Access Foundation 01.01.2022
Témata:
Artificial intelligence
Coders
Encoders-Decoders
Languages
Lifelong learning
Machine translation
Modular systems
Modules
Multilingualism
ISSN:1076-9757, 1076-9757, 1943-5037
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1076-9757
1076-9757
1943-5037
DOI:10.1613/jair.1.12699