Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
Not on the map. Why?
Abstract (arXiv)
Opinion summarization provides an important solution for summarizing opinions expressed among a large number of reviews. However, generating aspect-specific and general summaries is challenging due to the lack of annotated data. In this work, we propose two simple yet effective unsupervised approaches to generate both aspect-specific and general opinion summaries by training on synthetic datasets constructed with aspect-related review contents. Our first approach, Seed Words Based Leave-One-Out (SW-LOO), identifies aspect-related portions of reviews simply by exact-matching aspect seed words and outperforms existing methods by 3.4 ROUGE-L points on SPACE and 0.5 ROUGE-1 point on OPOSUM+ for aspect-specific opinion summarization. Our second approach, Natural Language Inference Based Leave-One-Out (NLI-LOO) identifies aspect-related sentences utilizing an NLI model in a more general setting without using seed words and outperforms existing approaches by 1.2 ROUGE-L points on SPACE for aspect-specific opinion summarization and remains competitive on other metrics.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 32 of its 57 references that are in the map. First posted on arXiv 21 Mar 2023.
Builds on
32 of 57 references.
References · 32
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2017Neural Discrete Representation Learningcited by 4,650
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
- 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
20 more
- 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
- 2015Image-based Recommendations on Styles and Substitutescited by 702
- 2019Text Summarization with Pretrained Encoderscited by 553
- 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
- 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 299
- 2020TLDR: Extreme Summarization of Scientific Documentscited by 136
- 2018Ranking Sentences for Extractive Summarization with Reinforcement Learningcited by 128
- 2020Extractive Opinion Summarization in Quantized Transformer Spacescited by 76
- 2018Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervisedcited by 75
- 2019Unsupervised Opinion Summarization as Copycat-Review Generationcited by 68
- 2021Aspect-Controllable Opinion Summarizationcited by 47
- 2016Neural Network-Based Abstract Generation for Opinions and Argumentscited by 46
- 2020Unsupervised Opinion Summarization with Noising and Denoisingcited by 37
- 2019Informative and Controllable Opinion Summarizationcited by 27
- 2020Unsupervised Opinion Summarization with Content Planningcited by 27
- 2020Self-Supervised and Controlled Multi-Document Opinion Summarizationcited by 23
- 2021Convex Aggregation for Opinion Summarizationcited by 21
- 2022Unsupervised Extractive Opinion Summarization Using Sparse Codingcited by 17
- 2022Efficient Few-Shot Fine-Tuning for Opinion Summarizationcited by 16
- 2021Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidancecited by 14
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.