Emergent Mind
From Bilingual to Multilingual Neural Machine Translation by Incremental Training
(1907.00735)
Published Jun 28, 2019
in
cs.CL
Abstract
Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that allows the system to scale to more languages without modification of the previous components based on joint training and language-independent encoder/decoder modules allowing for zero-shot translation. This work in progress shows close results to the state-of-the-art in the WMT task.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.