# Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking

arXiv: https://arxiv.org/abs/1906.05691 · HTML: https://mlsanity.com/paper/1906.05691/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [Unsupervised Extractive Opinion Summarization Using Sparse Coding](https://mlsanity.com/paper/2203.07921/) (2022)
- [Efficient Few-Shot Fine-Tuning for Opinion Summarization](https://mlsanity.com/paper/2205.02170/) (2022)
- [Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance](https://mlsanity.com/paper/2106.08007/) (2021)
- [OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization](https://mlsanity.com/paper/2310.18122/) (2023)
- [RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization](https://mlsanity.com/paper/2405.00657/) (2024)
- [Identifying Helpful Sentences in Product Reviews](https://mlsanity.com/paper/2104.09792/) (2021)
- [Multitask Learning for Class-Imbalanced Discourse Classification](https://mlsanity.com/paper/2101.00389/) (2021)
- [Polarity Calibration for Opinion Summarization](https://mlsanity.com/paper/2404.01706/) (2024)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)
- [RST-style Discourse Parsing Guided by Document-level Content Structures](https://mlsanity.com/paper/2309.04141/) (2023)
- [MOSAIC: Modular Opinion Summarization using Aspect Identification and Clustering](https://mlsanity.com/paper/2603.19277/) (2026)

## Abstract (arXiv)

This paper focuses on the end-to-end abstractive summarization of a single product review without supervision. We assume that a review can be described as a discourse tree, in which the summary is the root, and the child sentences explain their parent in detail. By recursively estimating a parent from its children, our model learns the latent discourse tree without an external parser and generates a concise summary. We also introduce an architecture that ranks the importance of each sentence on the tree to support summary generation focusing on the main review point. The experimental results demonstrate that our model is competitive with or outperforms other unsupervised approaches. In particular, for relatively long reviews, it achieves a competitive or better performance than supervised models. The induced tree shows that the child sentences provide additional information about their parent, and the generated summary abstracts the entire review.