In this paper, we propose a novel pretraining-based encoder-decoder
framework, which can generate the output sequence based on the input sequence
in a two-stage manner. For the encoder of our model, we encode the input
sequence into context representations using BERT. For the decoder, there are
two stages in our model, in the first stage, we use a Transformer-based decoder
to generate a draft output sequence. In the second stage, we mask each word of
the draft sequence and feed it to BERT, then by combining the input sequence
and the draft representation generated by BERT, we use a Transformer-based
decoder to predict the refined word for each masked position. To the best of
our knowledge, our approach is the first method which applies the BERT into
text generation tasks. As the first step in this direction, we evaluate our
proposed method on the text summarization task. Experimental results show that
our model achieves new state-of-the-art on both CNN/Daily Mail and New York
Times datasets.

本文提出了一种基于预训练的编码器 - 解码器框架，使用 BERT 编码输入序列来生成输出序列，采用 Transformer-based 解码器生成草稿输出序列，并将其与原始输入序列结合使用，使用 BERT 生成的草稿表示来预测遮罩位置的优化单词，进而在文本摘要任务上实现了最新的技术水平。