Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder
This addresses the problem of generating concise summaries from product reviews for consumers and businesses, though it is incremental as it builds on existing summarization methods.
The paper tackles abstractive review summarization by proposing a two-stage reinforcement learning approach that predicts word types (aspect, opinion, context) before generating summaries, achieving consistent improvements in ROUGE scores on Amazon product review datasets.
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 word distribution.Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.