# Cone: Unsupervised Contrastive Opinion Extraction

arXiv: https://arxiv.org/abs/2305.04599 · HTML: https://mlsanity.com/paper/2305.04599/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 8 May 2023.

## Builds on (most cited first, 22 of 22)

- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [CERT: Contrastive Self-supervised Learning for Language Understanding](https://mlsanity.com/paper/2005.12766/) (2020)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [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)
- [Topic Modeling with Wasserstein Autoencoders](https://mlsanity.com/paper/1907.12374/) (2019)
- [Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction](https://mlsanity.com/paper/1805.04601/) (2018)
- [Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations](https://mlsanity.com/paper/2202.04582/) (2022)
- [Unsupervised Extractive Opinion Summarization Using Sparse Coding](https://mlsanity.com/paper/2203.07921/) (2022)
- [Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learning](https://mlsanity.com/paper/2002.10198/) (2020)
- [Key Point Analysis via Contrastive Learning and Extractive Argument Summarization](https://mlsanity.com/paper/2109.15086/) (2021)
- [HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset](https://mlsanity.com/paper/2002.06854/) (2020)
- [Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification](https://mlsanity.com/paper/2009.03695/) (2020)
- [Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media](https://mlsanity.com/paper/2205.03296/) (2022)
- [Twitter Opinion Topic Model: Extracting Product Opinions from Tweets by Leveraging Hashtags and Sentiment Lexicon](https://mlsanity.com/paper/1609.06578/) (2016)

## Abstract (arXiv)

Contrastive opinion extraction aims to extract a structured summary or key points organised as positive and negative viewpoints towards a common aspect or topic. Most recent works for unsupervised key point extraction is largely built on sentence clustering or opinion summarisation based on the popularity of opinions expressed in text. However, these methods tend to generate aspect clusters with incoherent sentences, conflicting viewpoints, redundant aspects. To address these problems, we propose a novel unsupervised Contrastive OpinioN Extraction model, called Cone, which learns disentangled latent aspect and sentiment representations based on pseudo aspect and sentiment labels by combining contrastive learning with iterative aspect/sentiment clustering refinement. Apart from being able to extract contrastive opinions, it is also able to quantify the relative popularity of aspects and their associated sentiment distributions. The model has been evaluated on both a hotel review dataset and a Twitter dataset about COVID vaccines. The results show that despite using no label supervision or aspect-denoted seed words, Cone outperforms a number of competitive baselines on contrastive opinion extraction. The results of Cone can be used to offer a better recommendation of products and services online.