mlsanityData to 7 Oct 2026

Comparative Opinion Summarization via Collaborative Decoding

arXiv 2110.07520 ↗First posted 14 Oct 2021cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may be insufficient to help the user compare multiple different choices. Thus, the user may still struggle with the question "Which one should I pick?" In this paper, we propose the comparative opinion summarization task, which aims at generating two contrastive summaries and one common summary from two different candidate sets of reviews. We develop a comparative summarization framework CoCoSum, which consists of two base summarization models that jointly generate contrastive and common summaries. Experimental results on a newly created benchmark CoCoTrip show that CoCoSum can produce higher-quality contrastive and common summaries than state-of-the-art opinion summarization models. The dataset and code are available at https://github.com/megagonlabs/cocosum

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 31 of its 58 references that are in the map. First posted on arXiv 14 Oct 2021.

Builds on

31 of 58 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  10. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  11. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  12. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
19 more
  1. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  2. 2019Show Your Work: Improved Reporting of Experimental Resultscited by 164
  3. 2020GSum: A General Framework for Guided Neural Abstractive Summarizationcited by 129
  4. 2017Controllable Abstractive Summarizationcited by 110
  5. 2020CTRLsum: Towards Generic Controllable Text Summarizationcited by 98
  6. 2020Extractive Opinion Summarization in Quantized Transformer Spacescited by 76
  7. 2018Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervisedcited by 75
  8. 2019Unsupervised Opinion Summarization as Copycat-Review Generationcited by 68
  9. 2021Aspect-Controllable Opinion Summarizationcited by 47
  10. 2020Unsupervised Opinion Summarization with Noising and Denoisingcited by 37
  11. 2020OpinionDigest: A Simple Framework for Opinion Summarizationcited by 37
  12. 2020Unsupervised Opinion Summarization with Content Planningcited by 27
  13. 2020Self-Supervised and Controlled Multi-Document Opinion Summarizationcited by 23
  14. 2021Convex Aggregation for Opinion Summarizationcited by 21
  15. 2021Self-Supervised Multimodal Opinion Summarizationcited by 18
  16. 2021Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidancecited by 14
  17. 2021Inference Time Style Control for Summarizationcited by 13
  18. 2018Comparative Document Summarisation via Classificationcited by 2
  19. 2015Comparative Document Analysis for Large Text Corporacited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 9; 2025: 1; 2026: 3.

18 papers.

Sort:

By area:

  1. 2023Fair Abstractive Summarization of Diverse Perspectivescited by 17
  2. 2024From Single to Multi: How LLMs Hallucinate in Multi-Document Summarizationcited by 17
  3. 2024Bias in Opinion Summarisation from Pre-training to Adaptation: A Case Study in Political Biascited by 12
  4. 2024AmbigNLG: Addressing Task Ambiguity in Instruction for NLGcited by 10
  5. 2023Attributable and Scalable Opinion Summarizationcited by 6
  6. 2023Pre-training Language Models for Comparative Reasoningcited by 6
  7. 2024STRUM-LLM: Attributed and Structured Contrastive Summarizationcited by 4
  8. 2022Noisy Pairing and Partial Supervision for Stylized Opinion Summarizationcited by 3
  9. 2024Summarization of Opinionated Political Documents with Varied Perspectivescited by 3
  10. 2022Summarizing Community-based Question-Answer Pairscited by 2
  11. 2024Polarity Calibration for Opinion Summarizationcited by 2
  12. 2025Reranking-based Generation for Unbiased Perspective Summarizationcited by 2
6 more
  1. 2024Multi-Review Fusion-in-Contextcited by 1
  2. 2024Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMMcited by 1
  3. 2026Comparing Without Saying: A Dataset and Benchmark for Implicit Comparative Opinion Mining from Same-User Reviewscited by 1
  4. 2024CASPR: Automated Evaluation Metric for Contrastive Summarizationcited by 0
  5. 2026The Critical Role of Aspects in Measuring Document Similaritycited by 0
  6. 2026Automated Analysis of Global AI Safety Initiatives: A Taxonomy-Driven LLM Approachcited by 0