mlsanityData to 7 Oct 2026

Cone: Unsupervised Contrastive Opinion Extraction

arXiv 2305.04599 ↗First posted 8 May 2023cs.CLcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 8 May 2023.

Builds on

22 of 38 references.

References · 22

  1. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  2. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  5. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  6. 2019Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Modelcited by 431
  7. 2020Extractive Summarization as Text Matchingcited by 189
  8. 2020CERT: Contrastive Self-supervised Learning for Language Understandingcited by 169
  9. 2018Disentangled Representation Learning for Non-Parallel Text Style Transfercited by 127
  10. 2020Extractive Opinion Summarization in Quantized Transformer Spacescited by 76
  11. 2019Unsupervised Opinion Summarization as Copycat-Review Generationcited by 68
  12. 2020From Arguments to Key Points: Towards Automatic Argument Summarizationcited by 60
10 more
  1. 2019Topic Modeling with Wasserstein Autoencoderscited by 53
  2. 2018Double Embeddings and CNN-based Sequence Labeling for Aspect Extractioncited by 42
  3. 2022Topic Discovery via Latent Space Clustering of Pretrained Language Model Representationscited by 34
  4. 2022Unsupervised Extractive Opinion Summarization Using Sparse Codingcited by 17
  5. 2020Leveraging Code Generation to Improve Code Retrieval and Summarization via Dual Learningcited by 16
  6. 2021Key Point Analysis via Contrastive Learning and Extractive Argument Summarizationcited by 16
  7. 2020HotelRec: a Novel Very Large-Scale Hotel Recommendation Datasetcited by 14
  8. 2020Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classificationcited by 10
  9. 2022Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Mediacited by 4
  10. 2016Twitter Opinion Topic Model: Extracting Product Opinions from Tweets by Leveraging Hashtags and Sentiment Lexiconcited by 2

Built on by

Not cited yet.