Machine reading comprehension (MRC) is an important area of conversation agents and draws a lot of attention. However, there is a notable limitation to current MRC benchmarks: The labeled answers are mostly either spans extracted from the target corpus or the choices of the given candidates, ignoring the natural aspect of high-quality responses. As a result, MRC models trained on these datasets can not generate human-like responses in real QA scenarios. To this end, we construct a new dataset called Penguin to promote the research of MRC, providing a training and test bed for natural response generation to real scenarios. Concretely, Penguin consists of 200k training data with high-quality fluent, and well-informed responses. Penguin is the first benchmark towards natural response generation in Chinese MRC on a relatively large scale. To address the challenges in Penguin, we develop two strong baselines: end-to-end and two-stage frameworks. Following that, we further design Prompt-BART: fine-tuning the pre-trained generative language models with a mixture of prefix prompts in Penguin. Extensive experiments validated the effectiveness of this design.

In March 2020, as businesses across the world sent non-essential workers home to slow the spread of the coronavirus, a 2.6 million-sq.-ft. General Motors plant in Kokomo, Ind., sat idle. At the same time, ventilators--the breathing machines essential to keeping critically ill COVID-19 patients alive--were in frighteningly short supply. And so within a week of pausing the plant's operations, GM CEO Mary Barra launched it back into action, quickly transforming a dormant engineering building into an assembly line that delivered 30,000 ventilators in five months. Barra says that approach, incubated in the crisis of the pandemic, is now a permanent cultural shift that has already led to faster timetables for GM's bet-the-company push to sell only electric vehicles by 2035.