论文标题
神经同时使用基于对齐的块的语音翻译
Neural Simultaneous Speech Translation Using Alignment-Based Chunking
论文作者
论文摘要
在同时的机器翻译中，目的是确定何时在源单词连续流中产生部分翻译，并在延迟和质量之间进行权衡。我们提出了一个神经机器翻译（NMT）模型，该模型在继续以输入或生成输出单词为食的时候做出动态决策。该模型由两个主要组成部分组成：一个要动态决定结束源块，而另一个可以翻译消耗的块。我们以与推理条件一致的方式共同训练组件。为了生成块的培训数据，我们提出了一种利用单词对齐的方法，同时还可以保留足够的上下文。我们将模型与不同深度的双向和单向编码器进行比较，无论是在真实的语音和文本输入上。我们在IWSLT 2020英语至德任务上的结果优于等待K的基线，而BLEU绝对是2.6％至3.7％。
In simultaneous machine translation, the objective is to determine when to produce a partial translation given a continuous stream of source words, with a trade-off between latency and quality. We propose a neural machine translation (NMT) model that makes dynamic decisions when to continue feeding on input or generate output words. The model is composed of two main components: one to dynamically decide on ending a source chunk, and another that translates the consumed chunk. We train the components jointly and in a manner consistent with the inference conditions. To generate chunked training data, we propose a method that utilizes word alignment while also preserving enough context. We compare models with bidirectional and unidirectional encoders of different depths, both on real speech and text input. Our results on the IWSLT 2020 English-to-German task outperform a wait-k baseline by 2.6 to 3.7% BLEU absolute.
