Leveraging Diverse Modeling Contexts with Collaborating Learning for Neural Machine Translation

arXiv:2402.18428v1 Announce Type: new
Abstract: Autoregressive (AR) and Non-autoregressive (NAR) models are two types of generative models for Neural Machine Translation (NMT). AR models predict tokens in a word-by-word manner and can effectively capture the distribution of real translations. NAR models predict tokens by extracting bidirectional contextual information which can improve the inference speed but they suffer from performance degradation. Previous works utilized AR models to enhance NAR models by reducing the training data's complexity or incorporating the global information …

abstract arxiv cs.cl distribution diverse generative generative models information machine machine translation modeling neural machine translation tokens translation type types word