# Unsupervised Opinion Summarization as Copycat-Review Generation

arXiv: https://arxiv.org/abs/1911.02247 · HTML: https://mlsanity.com/paper/1911.02247/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2019.

## Built on by (most cited first, 30 of 68)

- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [Aspect-Controllable Opinion Summarization](https://mlsanity.com/paper/2109.03171/) (2021)
- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining](https://mlsanity.com/paper/2106.00829/) (2021)
- [Learning Opinion Summarizers by Selecting Informative Reviews](https://mlsanity.com/paper/2109.04325/) (2021)
- [Convex Aggregation for Opinion Summarization](https://mlsanity.com/paper/2104.01371/) (2021)
- [BASS: Boosting Abstractive Summarization with Unified Semantic Graph](https://mlsanity.com/paper/2105.12041/) (2021)
- [Every Bite Is an Experience: Key Point Analysis of Business Reviews](https://mlsanity.com/paper/2106.06758/) (2021)
- [Self-Supervised Multimodal Opinion Summarization](https://mlsanity.com/paper/2105.13135/) (2021)
- [Comparative Opinion Summarization via Collaborative Decoding](https://mlsanity.com/paper/2110.07520/) (2021)
- [Unsupervised Extractive Opinion Summarization Using Sparse Coding](https://mlsanity.com/paper/2203.07921/) (2022)
- [Fair Abstractive Summarization of Diverse Perspectives](https://mlsanity.com/paper/2311.07884/) (2023)
- [Efficient Few-Shot Fine-Tuning for Opinion Summarization](https://mlsanity.com/paper/2205.02170/) (2022)
- [One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation](https://mlsanity.com/paper/2402.11683/) (2024)
- [Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance](https://mlsanity.com/paper/2106.08007/) (2021)
- [Factual and Informative Review Generation for Explainable Recommendation](https://mlsanity.com/paper/2209.12613/) (2022)
- [Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation](https://mlsanity.com/paper/2305.14647/) (2023)
- [Examining Bias in Opinion Summarisation Through the Perspective of Opinion Diversity](https://mlsanity.com/paper/2306.04424/) (2023)
- [OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization](https://mlsanity.com/paper/2310.18122/) (2023)
- [Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Bias](https://mlsanity.com/paper/2402.00322/) (2024)
- [DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation](https://mlsanity.com/paper/2106.00791/) (2021)
- [Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets](https://mlsanity.com/paper/2310.13340/) (2023)
- [Identifying Helpful Sentences in Product Reviews](https://mlsanity.com/paper/2104.09792/) (2021)
- [Beyond Opinion Mining: Summarizing Opinions of Customer Reviews](https://mlsanity.com/paper/2206.01543/) (2022)
- [Template-based Abstractive Microblog Opinion Summarisation](https://mlsanity.com/paper/2208.04083/) (2022)
- [From Key Points to Key Point Hierarchy: Structured and Expressive Opinion Summarization](https://mlsanity.com/paper/2306.03853/) (2023)
- [Hierarchical Indexing for Retrieval-Augmented Opinion Summarization](https://mlsanity.com/paper/2403.00435/) (2024)
- [Attributable and Scalable Opinion Summarization](https://mlsanity.com/paper/2305.11603/) (2023)
- ["What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge](https://mlsanity.com/paper/2305.12091/) (2023)
- [Product Description and QA Assisted Self-Supervised Opinion Summarization](https://mlsanity.com/paper/2404.05243/) (2024)

## Abstract (arXiv)

Opinion summarization is the task of automatically creating summaries that reflect subjective information expressed in multiple documents, such as product reviews. While the majority of previous work has focused on the extractive setting, i.e., selecting fragments from input reviews to produce a summary, we let the model generate novel sentences and hence produce abstractive summaries. Recent progress in summarization has seen the development of supervised models which rely on large quantities of document-summary pairs. Since such training data is expensive to acquire, we instead consider the unsupervised setting, in other words, we do not use any summaries in training. We define a generative model for a review collection which capitalizes on the intuition that when generating a new review given a set of other reviews of a product, we should be able to control the "amount of novelty" going into the new review or, equivalently, vary the extent to which it deviates from the input. At test time, when generating summaries, we force the novelty to be minimal, and produce a text reflecting consensus opinions. We capture this intuition by defining a hierarchical variational autoencoder model. Both individual reviews and the products they correspond to are associated with stochastic latent codes, and the review generator ("decoder") has direct access to the text of input reviews through the pointer-generator mechanism. Experiments on Amazon and Yelp datasets, show that setting at test time the review's latent code to its mean, allows the model to produce fluent and coherent summaries reflecting common opinions.