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

2021/01/26 by Saravanakumar, Kailash Karthik, Ballesteros, Miguel, Chandrasekaran, Muthu Kumar +1 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2101.11059

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.

Cited by

• EventHunter: Dynamic Clustering and Ranking of Security Events from Hacker Forum Discussions

Related

• Multilingual Clustering of Streaming News
• Contextualization for the Organization of Text Documents Streams
• Content-driven, unsupervised clustering of news articles through multiscale graph partitioning
• Large Language Model Enhanced Clustering for News Event Detection
• Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics