# Event-Driven News Stream Clustering using Entity-Aware Contextual Embeddings

arXiv: https://arxiv.org/abs/2101.11059 · HTML: https://mlsanity.com/paper/2101.11059/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 26 Jan 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Zero-Shot Entity Linking by Reading Entity Descriptions](https://mlsanity.com/paper/1906.07348/) (2019)
- [Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!](https://mlsanity.com/paper/2004.14914/) (2020)
- [The Dynamic Embedded Topic Model](https://mlsanity.com/paper/1907.05545/) (2019)
- [Multilingual Clustering of Streaming News](https://mlsanity.com/paper/1809.00540/) (2018)
- [Batch Clustering for Multilingual News Streaming](https://mlsanity.com/paper/2004.08123/) (2020)
- [Discovering topic structures of a temporally evolving document corpus](https://mlsanity.com/paper/1512.08008/) (2015)
- [Inductive Document Network Embedding with Topic-Word Attention](https://mlsanity.com/paper/2001.03369/) (2020)
- [Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time](https://mlsanity.com/paper/1711.05626/) (2017)
- [Neural Embedding Allocation: Distributed Representations of Topic Models](https://mlsanity.com/paper/1909.04702/) (2019)

## Built on by (most cited first, 12 of 12)

- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding](https://mlsanity.com/paper/2406.02472/) (2024)
- [Unsupervised Key Event Detection from Massive Text Corpora](https://mlsanity.com/paper/2206.04153/) (2022)
- [DIGAT: Modeling News Recommendation with Dual-Graph Interaction](https://mlsanity.com/paper/2210.05196/) (2022)
- [Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding](https://mlsanity.com/paper/2304.04099/) (2023)
- [SCStory: Self-supervised and Continual Online Story Discovery](https://mlsanity.com/paper/2312.03725/) (2023)
- [Simplifying Multilingual News Clustering Through Projection From a Shared Space](https://mlsanity.com/paper/2204.13418/) (2022)
- [Tracking the Takes and Trajectories of English-Language News Narratives across Trustworthy and Worrisome Websites](https://mlsanity.com/paper/2501.09102/) (2025)
- [EventHunter: Dynamic Clustering and Ranking of Security Events from Hacker Forum Discussions](https://mlsanity.com/paper/2507.09762/) (2025)
- [Topic-time Heatmaps for Human-in-the-loop Topic Detection and Tracking](https://mlsanity.com/paper/2110.07337/) (2021)
- [Topic Detection and Tracking with Time-Aware Document Embeddings](https://mlsanity.com/paper/2112.06166/) (2021)
- [TingIS: Real-time Risk Event Discovery from Noisy Customer Incidents at Enterprise Scale](https://mlsanity.com/paper/2604.21889/) (2026)

## Abstract (arXiv)

We propose a method for online news stream clustering that is a variant of the non-parametric streaming K-means algorithm. Our model uses a combination of sparse and dense document representations, aggregates document-cluster similarity along these multiple representations and makes the clustering decision using a neural classifier. The weighted document-cluster similarity model is learned using a novel adaptation of the triplet loss into a linear classification objective. We show that the use of a suitable fine-tuning objective and external knowledge in pre-trained transformer models yields significant improvements in the effectiveness of contextual embeddings for clustering. Our model achieves a new state-of-the-art on a standard stream clustering dataset of English documents.