mlsanityData to 7 Oct 2026

Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding

arXiv 2304.04099 ↗First posted 8 Apr 2023cs.IR cs.CL cs.DBcited by 5

Not on the map. Why?

Abstract (arXiv)

Unsupervised discovery of stories with correlated news articles in real-time helps people digest massive news streams without expensive human annotations. A common approach of the existing studies for unsupervised online story discovery is to represent news articles with symbolic- or graph-based embedding and incrementally cluster them into stories. Recent large language models are expected to improve the embedding further, but a straightforward adoption of the models by indiscriminately encoding all information in articles is ineffective to deal with text-rich and evolving news streams. In this work, we propose a novel thematic embedding with an off-the-shelf pretrained sentence encoder to dynamically represent articles and stories by considering their shared temporal themes. To realize the idea for unsupervised online story discovery, a scalable framework USTORY is introduced with two main techniques, theme- and time-aware dynamic embedding and novelty-aware adaptive clustering, fueled by lightweight story summaries. A thorough evaluation with real news data sets demonstrates that USTORY achieves higher story discovery performances than baselines while being robust and scalable to various streaming settings.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 57 references that are in the map. First posted on arXiv 8 Apr 2023.

Builds on

25 of 57 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2014Distributed Representations of Sentences and Documentscited by 677
  6. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  7. 2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 111
  8. 2020Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!cited by 73
  9. 2020A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portalcited by 72
  10. 2020Generating Representative Headlines for News Storiescited by 39
  11. 2020Text Classification Using Label Names Only: A Language Model Self-Training Approachcited by 32
  12. 2022TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel Topic Clusterscited by 30
13 more
  1. 2021NewsBERT: Distilling Pre-trained Language Model for Intelligent News Applicationcited by 17
  2. 2018Multilingual Clustering of Streaming Newscited by 14
  3. 2022ProFairRec: Provider Fairness-aware News Recommendationcited by 13
  4. 2022Adaptive Model Pooling for Online Deep Anomaly Detection from a Complex Evolving Data Streamcited by 13
  5. 2021Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddingscited by 12
  6. 2020Batch Clustering for Multilingual News Streamingcited by 9
  7. 2018Growing Story Forest Online from Massive Breaking Newscited by 7
  8. 2022Unsupervised Key Event Detection from Massive Text Corporacited by 7
  9. 2022Topic Taxonomy Expansion via Hierarchy-Aware Topic Phrase Generationcited by 7
  10. 2023PDSum: Prototype-driven Continuous Summarization of Evolving Multi-document Sets Streamcited by 7
  11. 2021NewsEmbed: Modeling News through Pre-trained Document Representationscited by 6
  12. 2019Mining News Events from Comparable News Corpora: A Multi-Attribute Proximity Network Modeling Approachcited by 2
  13. 2022Simplifying Multilingual News Clustering Through Projection From a Shared Spacecited by 1

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  2. 2023Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detectioncited by 15
  3. 2024Online Drift Detection with Maximum Concept Discrepancycited by 12
  4. 2024Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Eventscited by 1
  5. 2026CREAM: Continual Retrieval on Dynamic Streaming Corpora with Adaptive Soft Memorycited by 1