TL;DR本文提出了一种新的架构,通过使用混合指针生成网络和覆盖机制以增强标准的序列到序列注意模型来解决神经序列到序列模型不精确复制信息和重复问题,该模型在 CNN/Daily Mail 摘要任务上表现优异。
Abstract
neural sequence-to-sequence models have provided a viable new approach for
abstractive text summarization (meaning they are not restricted to simply
selecting and rearranging passages from the original text). How