Small pre-trained model for background understanding in multi-round question answering

Multi-round Q&A based on background text needs to infer the answer to the question through the current question, historical Q&A pairs, and background text. The pre-trained model has proved its effectiveness in this task; however, the existing model has many problems such as too many parameters and high resource consumption. We propose a knowledge transfer method that combines knowledge distillation, co-learning of similar datasets, and fine-tuning of similar tasks. Through multi-knowledge cooperative training from large model to small model, between different data sets, and between different tasks, the performance of the small model with low resource consumption can match or surpass that of the large model.