Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events

TL;DR

This paper presents EpiMine, an unsupervised framework that combines episodic structure detection with large language models to improve large-scale news event identification, addressing interpretability and adaptability challenges.

Contribution

Introducing the novel task of episode detection in news corpora and developing EpiMine, which leverages natural episodic partitions and LLMs for enhanced event detection.

Findings

EpiMine achieves a 59.2% average gain over baselines.

EpiMine effectively identifies cohesive episodes in diverse datasets.

The framework improves interpretability and adaptability in event detection.

Abstract

State-of-the-art automatic event detection struggles with interpretability and adaptability to evolving large-scale key events -- unlike episodic structures, which excel in these areas. Often overlooked, episodes represent cohesive clusters of core entities performing actions at a specific time and location; a partially ordered sequence of episodes can represent a key event. This paper introduces a novel task, episode detection, which identifies episodes within a news corpus of key event articles. Detecting episodes poses unique challenges, as they lack explicit temporal or locational markers and cannot be merged using semantic similarity alone. While large language models (LLMs) can aid with these reasoning difficulties, they suffer with long contexts typical of news corpora. To address these challenges, we introduce EpiMine, an unsupervised framework that identifies a key event's candidate episodes by leveraging natural episodic partitions in articles, estimated through shifts in discriminative term combinations. These candidate episodes are more cohesive and representative of true episodes, synergizing with LLMs to better interpret and refine them into final episodes. We apply EpiMine to our three diverse, real-world event datasets annotated at the episode level, where it achieves a 59.2% average gain across all metrics compared to baselines.