Learning to Multi-Task Learn for Better Neural Machine Translation

Scarcity of parallel sentence pairs is a major challenge for training high quality neural machine translation (NMT) models in bilingually low-resource scenarios, as NMT is data-hungry. Multi-task learning is an elegant approach to inject linguistic-related inductive biases into NMT, using auxiliary syntactic and semantic tasks, to improve generalisation. The challenge, however, is to devise effective training schedules, prescribing when to make use of the auxiliary tasks during the training process to fill the knowledge gaps of the main translation task, a setting referred to as biased-MTL. Current approaches for the training schedule are based on hand-engineering heuristics, whose effectiveness vary in different MTL settings. We propose a novel framework for learning the training schedule, ie learning to multi-task learn, for the MTL setting of interest. We formulate the training schedule as a Markov decision process which paves the way to employ policy learning methods to learn the scheduling policy. We effectively and efficiently learn the training schedule policy within the imitation learning framework using an oracle policy algorithm that dynamically sets the importance weights of auxiliary tasks based on their contributions to the generalisability of the main NMT task. Experiments on low-resource NMT settings show the resulting automatically learned training schedulers are competitive with the best heuristics, and lead to up to +1.1 BLEU score improvements.