We propose InsNet, an expressive insertion-based text generator with efficient training and flexible decoding (parallel or sequential). Unlike most existing insertion-based text generation works that require re-encoding of the context after each insertion operation and thus are inefficient to train, InsNet only requires one pass of context encoding for the entire insertion sequence during training by introducing a novel insertion-oriented position encoding to enable computation sharing. Experiments on two unsupervised lexically constrained text generation datasets and three machine translation datasets demonstrate InsNet's advantages over previous insertion-based methods in terms of training speed, inference efficiency, and generation quality.

翻译：我们建议 InsNet, 是一个有高效培训和灵活解码(平行或相继)的基于插入的文本生成器。 与大多数现有的基于插入的文本生成工程不同,这些工程需要在每次插入操作后对上下文重新编码,因而培训效率低下。 InsNet只需要在培训期间对整个插入序列进行一次上下文编码,即引入一种新的以插入为导向的位置编码,以便能够进行计算共享。 在两个不受法律监管的文本生成数据集和三个机器翻译数据集上进行的实验表明,InsNet在培训速度、推断效率和生成质量方面比以往基于插入的方法具有优势。