Generative reading understanding method based on multi-task learning

The invention provides a multi-task learning-based generative reading understanding method. The method comprises the following steps of obtaining a target question and a target paragraph, obtaining feature vectors corresponding to the target question and the target paragraph, inputting the feature vectors into a target reading understanding model, and obtaining a target answer; therefore, the accuracy and reliability of the target answer are improved. 本发明提供了一种基于多任务学习的生成式阅读理解方法，所述方法包括如下步骤：获取目标问题和目标段落，获取目标问题和目标段落的对应的特征向量，将特征向量输入到目标阅读理解模型，获取目标答案；从而提高目标答案的准确性和可靠性。