# Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder

arXiv: https://arxiv.org/abs/2004.05755 · HTML: https://mlsanity.com/paper/2004.05755/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 4 of 4)

- [Unsupervised Extractive Opinion Summarization Using Sparse Coding](https://mlsanity.com/paper/2203.07921/) (2022)
- [TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary Generation](https://mlsanity.com/paper/2206.00847/) (2022)
- [A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare](https://mlsanity.com/paper/2310.18354/) (2023)
- [MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering](https://mlsanity.com/paper/2603.19277/) (2026)

## Abstract (arXiv)

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.