基于Markov变换的级联文本生成（CS CL）---蔡秋纯

两种主要的神经文本生成方法是完全自回归模型，使用串行波束搜索解码，和非自回归模型，使用无输出依赖的并行解码。提出了一种具有次线性并行时间生成的自回归模型。考虑到上下文有界的条件随机场可以并行解码，我们提出了一种高效的级联解码方法来产生高质量的输出。为了参数化这个级联，我们引入了一个Markov变换器，一个流行的完全自回归模型的变体，它允许我们同时解码特定的自回归上下文截断。这种方法只需要对标准的自回归训练稍加修改，同时与五个机器翻译数据集上的现有方法相比，显示出具有竞争力的准确性/速度折衷。

原文标题：Cascaded Text Generation with Markov Transformers

原文：The two dominant approaches to neural text generation are fully autoregressive models, using serial beam search decoding, and non-autoregressive models, using parallel decoding with no output dependencies. This work proposes an autoregressive model with sub-linear parallel time generation. Noting that conditional random fields with bounded context can be decoded in parallel, we propose an efficient cascaded decoding approach for generating high-quality output. To parameterize this cascade, we introduce a Markov transformer, a variant of the popular fully autoregressive model that allows us to simultaneously decode with specific autoregressive context cutoffs. This approach requires only a small modification from standard autoregressive training, while showing competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.

原文作者：Yuntian Deng, Alexander M. Rush

原文地址：https://arxiv.org/abs/2006.01112