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

TL;DR

This paper introduces an advanced online news stream clustering method that leverages entity-aware contextual embeddings and a neural classifier, significantly improving clustering accuracy on standard datasets.

Contribution

It presents a novel clustering approach combining sparse and dense representations with a triplet loss adaptation for improved effectiveness.

Findings

Achieves state-of-the-art results on news stream clustering datasets.

Utilizes fine-tuned transformer models with external knowledge for better embeddings.

Demonstrates significant improvements over existing clustering methods.

Abstract

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.