Progressive Multi-Granularity Training for Non-Autoregressive Translation
This addresses a specific bottleneck in machine translation for researchers and practitioners, but it is incremental as it builds on existing NAT methods.
The paper tackles the problem of non-autoregressive translation (NAT) being weak at learning high-mode knowledge like one-to-many translations by proposing progressive multi-granularity training, which improves phrase translation accuracy and reordering ability, resulting in better translation quality across multiple language pairs.
Non-autoregressive translation (NAT) significantly accelerates the inference process via predicting the entire target sequence. However, recent studies show that NAT is weak at learning high-mode of knowledge such as one-to-many translations. We argue that modes can be divided into various granularities which can be learned from easy to hard. In this study, we empirically show that NAT models are prone to learn fine-grained lower-mode knowledge, such as words and phrases, compared with sentences. Based on this observation, we propose progressive multi-granularity training for NAT. More specifically, to make the most of the training data, we break down the sentence-level examples into three types, i.e. words, phrases, sentences, and with the training goes, we progressively increase the granularities. Experiments on Romanian-English, English-German, Chinese-English, and Japanese-English demonstrate that our approach improves the phrase translation accuracy and model reordering ability, therefore resulting in better translation quality against strong NAT baselines. Also, we show that more deterministic fine-grained knowledge can further enhance performance.