Improving semi-autoregressive machine translation with the guidance of syntactic dependency parsing structure

The advent of non-autoregressive machine translation (NAT) accelerates the decoding superior to autoregressive machine translation (AT) significantly, while bringing about a performance decrease. Semi-autoregressive neural machine translation (SAT), as a compromise, enjoys the merits of both autoregressive and nonautoregressive decoding. However, current SAT methods face the challenges of information-limited initialization and rigorous termination. This paper develops a layer-and-length-based syntactic labeling method and introduces a syntactic dependency parsing structure-guided two-stage semi-autoregressive translation (SDPSAT) structure, which addresses the above challenges with a syntax-based initialization and termination. Additionally, we also present a Mixed Training strategy to shrink exposure bias. Experiments on seven widelyused datasets reveal that our SDPSAT surpasses traditional SAT models with reduced word repetition and achieves competitive results with the AT baseline at a 2x similar to 3x speedup.