Revisiting Modularized Multilingual NMT to Meet Industrial Demands

10/19/2020
by   Sungwon Lyu, et al.
0

The complete sharing of parameters for multilingual translation (1-1) has been the mainstream approach in current research. However, degraded performance due to the capacity bottleneck and low maintainability hinders its extensive adoption in industries. In this study, we revisit the multilingual neural machine translation model that only share modules among the same languages (M2) as a practical alternative to 1-1 to satisfy industrial requirements. Through comprehensive experiments, we identify the benefits of multi-way training and demonstrate that the M2 can enjoy these benefits without suffering from the capacity bottleneck. Furthermore, the interlingual space of the M2 allows convenient modification of the model. By leveraging trained modules, we find that incrementally added modules exhibit better performance than singly trained models. The zero-shot performance of the added modules is even comparable to supervised models. Our findings suggest that the M2 can be a competent candidate for multilingual translation in industries.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2019

From Bilingual to Multilingual Neural Machine Translation by Incremental Training

Multilingual Neural Machine Translation approaches are based on the use ...
research
09/16/2019

Multilingual Neural Machine Translation for Zero-Resource Languages

In recent years, Neural Machine Translation (NMT) has been shown to be m...
research
02/12/2021

Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders

Recently, universal neural machine translation (NMT) with shared encoder...
research
12/13/2021

English2Gbe: A multilingual machine translation model for Fon/EweGbe

Language is an essential factor of emancipation. Unfortunately, most of ...
research
05/23/2023

One-stop Training of Multiple Capacity Models for Multilingual Machine Translation

Training models with varying capacities can be advantageous for deployin...
research
05/21/2023

Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter

Federated Multilingual Neural Machine Translation (Fed-MNMT) has emerged...
research
02/25/2021

Tuning as a Means of Assessing the Benefits of New Ideas in Interplay with Existing Algorithmic Modules

Introducing new algorithmic ideas is a key part of the continuous improv...

Please sign up or login with your details

Forgot password? Click here to reset