2019/11/21 by Chenze Shao, Shao, Chenze, Jinchao Zhang +7 · 6 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1911.09320
openalex publication_date 2019/11/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Non-Autoregressive Neural Machine Translation (NAT) achieves significant decoding speedup through generating target words independently and simultaneously. However, in the context of non-autoregressive translation, the word-level cross-entropy loss cannot model the target-side sequential dependency properly, leading to its weak correlation with the translation quality. As a result, NAT tends to generate influent translations with over-translation and under-translation errors. In this paper, we propose to train NAT to minimize the Bag-of-Ngrams (BoN) difference between the model output and the reference sentence. The bag-of-ngrams training objective is differentiable and can be efficiently calculated, which encourages NAT to capture the target-side sequential dependency and correlates well with the translation quality. We validate our approach on three translation tasks and show that our approach largely outperforms the NAT baseline by about 5.0 BLEU scores on WMT14 En↔De and about 2.5 BLEU scores on WMT16 En↔Ro.