论文标题
将局部翻译机制纳入非自动收入的翻译
Incorporating a Local Translation Mechanism into Non-autoregressive Translation
论文作者
论文摘要
在这项工作中，我们将新型的本地自回旋翻译（LAT）机制介绍到非自动回旋翻译（NAT）模型中，以捕获焦油盖输出之间的局部依赖性。具体而言，对于每个目标解码位置，而不是仅一个令牌，我们以自动回归方式预测了一个简短的令牌序列。我们进一步设计了一种有效的合并算法，以将额外的零件对齐并将其合并为最终的输出序列。我们将LAT集成到条件蒙版的语言模型（CMLM; Ghazvininejad等，2019）中，并同样采用迭代解码。五个翻译任务的经验结果表明，与CMLM相比，我们的方法可实现可比性或更好的性能，而解码的迭代较少，带来了2.5倍的速度。进一步的分析表明，我们的方法减少了重复的翻译，并且在更长的句子中的性能更好。
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.
