Incorporating a Local Translation Mechanism into Non-autoregressive Translation
This work addresses efficiency and accuracy issues in machine translation for NLP practitioners, though it is incremental as it builds on existing CMLM methods.
The paper tackles the problem of capturing local dependencies in non-autoregressive translation models by introducing a local autoregressive translation mechanism, achieving comparable or better performance with a 2.5x speedup in decoding iterations.
In this work, we introduce a novel local autoregressive translation (LAT) mechanism into non-autoregressive translation (NAT) models so as to capture local dependencies among tar-get outputs. Specifically, for each target decoding position, instead of only one token, we predict a short sequence of tokens in an autoregressive way. We further design an efficient merging algorithm to align and merge the out-put pieces into one final output sequence. We integrate LAT into the conditional masked language model (CMLM; Ghazvininejad et al.,2019) and similarly adopt iterative decoding. Empirical results on five translation tasks show that compared with CMLM, our method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5xspeedup. Further analysis indicates that our method reduces repeated translations and performs better at longer sentences.