# From Key Points to Key Point Hierarchy: Structured and Expressive Opinion Summarization

arXiv: https://arxiv.org/abs/2306.03853 · HTML: https://mlsanity.com/paper/2306.03853/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Extractive Opinion Summarization in Quantized Transformer Spaces](https://mlsanity.com/paper/2012.04443/) (2020)
- [Unsupervised Opinion Summarization as Copycat-Review Generation](https://mlsanity.com/paper/1911.02247/) (2019)
- [From Arguments to Key Points: Towards Automatic Argument Summarization](https://mlsanity.com/paper/2005.01619/) (2020)
- [Quantitative Argument Summarization and Beyond: Cross-Domain Key Point Analysis](https://mlsanity.com/paper/2010.05369/) (2020)
- [Every Bite Is an Experience: Key Point Analysis of Business Reviews](https://mlsanity.com/paper/2106.06758/) (2021)
- [SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts](https://mlsanity.com/paper/2104.08809/) (2021)
- [CoRefi: A Crowd Sourcing Suite for Coreference Annotation](https://mlsanity.com/paper/2010.02588/) (2020)
- [Entailment Graph Learning with Textual Entailment and Soft Transitivity](https://mlsanity.com/paper/2204.03286/) (2022)
- [OpineSum: Entailment-based self-training for abstractive opinion summarization](https://mlsanity.com/paper/2212.10791/) (2022)

## Built on by (most cited first, 8 of 8)

- [An Empirical Analysis of Diversity in Argument Summarization](https://mlsanity.com/paper/2402.01535/) (2024)
- [Hierarchical Indexing for Retrieval-Augmented Opinion Summarization](https://mlsanity.com/paper/2403.00435/) (2024)
- [A Hybrid Intelligence Method for Argument Mining](https://mlsanity.com/paper/2403.09713/) (2024)
- [Exploring Key Point Analysis with Pairwise Generation and Graph Partitioning](https://mlsanity.com/paper/2404.11384/) (2024)
- [Random Tree Model of Meaningful Memory](https://mlsanity.com/paper/2412.01806/) (2024)
- [Decomposed Opinion Summarization with Verified Aspect-Aware Modules](https://mlsanity.com/paper/2501.17191/) (2025)
- [CHAMP: Efficient Annotation and Consolidation of Cluster Hierarchies](https://mlsanity.com/paper/2311.11301/) (2023)
- [A Community-Based Approach for Stance Distribution and Argument Organization](https://mlsanity.com/paper/2604.16852/) (2026)

## Abstract (arXiv)

Key Point Analysis (KPA) has been recently proposed for deriving fine-grained insights from collections of textual comments. KPA extracts the main points in the data as a list of concise sentences or phrases, termed key points, and quantifies their prevalence. While key points are more expressive than word clouds and key phrases, making sense of a long, flat list of key points, which often express related ideas in varying levels of granularity, may still be challenging. To address this limitation of KPA, we introduce the task of organizing a given set of key points into a hierarchy, according to their specificity. Such hierarchies may be viewed as a novel type of Textual Entailment Graph. We develop ThinkP, a high quality benchmark dataset of key point hierarchies for business and product reviews, obtained by consolidating multiple annotations. We compare different methods for predicting pairwise relations between key points, and for inferring a hierarchy from these pairwise predictions. In particular, for the task of computing pairwise key point relations, we achieve significant gains over existing strong baselines by applying directional distributional similarity methods to a novel distributional representation of key points, and further boost performance via weak supervision.