Non-autoregressive Machine Translation with Disentangled Context Transformer

Jungo Kasai, James Cross, Marjan Ghazvininejad, Jiatao Gu,

Abstract Paper

Thu Jul 16 5 p.m. PDT [iCal] [ Join Zoom ]
Fri Jul 17 4 a.m. PDT [iCal] [ Join Zoom ]
Please do not share or post zoom links

Abstract:

State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens. The sequential nature of this generation process causes fundamental latency in inference since we cannot generate multiple tokens in each sentence in parallel. We propose an attention-masking based model, called Disentangled Context (DisCo) transformer, that simultaneously generates all tokens given different contexts. The DisCo transformer is trained to predict every output token given an arbitrary subset of the other reference tokens. We also develop the parallel easy-first inference algorithm, which iteratively refines every token in parallel and reduces the number of required iterations. Our extensive experiments on 7 translation directions with varying data sizes demonstrate that our model achieves competitive, if not better, performance compared to the state of the art in non-autoregressive machine translation while significantly reducing decoding time on average.

Chat is not available.