We propose the Insertion-Deletion Transformer, a novel transformer-based neural architecture and training method for sequence generation. The model consists of two phases that are executed iteratively, 1) an insertion phase and 2) a deletion phase. The insertion phase parameterizes a distribution of insertions on the current output hypothesis, while the deletion phase parameterizes a distribution of deletions over the current output hypothesis. The training method is a principled and simple algorithm, where the deletion model obtains its signal directly on-policy from the insertion model output. We demonstrate the effectiveness of our Insertion-Deletion Transformer on synthetic translation tasks, obtaining significant BLEU score improvement over an insertion-only model.

中文翻译：

---

插入-删除转换器

我们提出了插入-删除变换器，这是一种基于变换器的新型神经架构和序列生成训练方法。该模型由两个迭代执行的阶段组成，1）插入阶段和 2）删除阶段。插入阶段参数化当前输出假设上的插入分布，而删除阶段参数化当前输出假设上的删除分布。训练方法是一种有原则且简单的算法，其中删除模型直接从插入模型输出中获得其信号。我们证明了我们的插入-删除转换器在合成翻译任务上的有效性，与仅插入模型相比，获得了显着的 BLEU 分数改进。