Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder
Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 2061-2064, 2019.
In this paper, we study abstractive review summarization. Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final w...More
PPT (Upload PPT)