# Pretraining-Based Natural Language Generation for Text Summarization

## TL;DR

This paper introduces a novel encoder-decoder framework that leverages BERT for text summarization, achieving state-of-the-art results by combining pretraining with a two-stage generation process.

## Contribution

It is the first to incorporate BERT into text generation, proposing a two-stage decoding process for improved summarization performance.

## Key findings

- Achieved new state-of-the-art results on CNN/Daily Mail dataset.
- Demonstrated effectiveness of BERT in text generation tasks.
- Validated the approach on New York Times dataset.

## Abstract

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.