LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World

TL;DR

LEMONADE is a comprehensive multilingual dataset of conflict events with novel abstractive extraction methods, evaluated with large language models, highlighting current zero-shot limitations and future research directions.

Contribution

The paper introduces LEMONADE, a large-scale multilingual conflict event dataset, and proposes abstractive event extraction and entity linking methods evaluated with LLMs.

Findings

Zero-shot systems achieve 58.3% F1 in event extraction.

ZEST surpasses OneNet with 45.7% F1 in entity linking.

Zero-shot methods still lag behind supervised models by 20-37%.

Abstract

This paper presents LEMONADE, a large-scale conflict event dataset comprising 39,786 events across 20 languages and 171 countries, with extensive coverage of region-specific entities. LEMONADE is based on a partially reannotated subset of the Armed Conflict Location & Event Data (ACLED), which has documented global conflict events for over a decade. To address the challenge of aggregating multilingual sources for global event analysis, we introduce abstractive event extraction (AEE) and its subtask, abstractive entity linking (AEL). Unlike conventional span-based event extraction, our approach detects event arguments and entities through holistic document understanding and normalizes them across the multilingual dataset. We evaluate various large language models (LLMs) on these tasks, adapt existing zero-shot event extraction systems, and benchmark supervised models. Additionally, we introduce ZEST, a novel zero-shot retrieval-based system for AEL. Our best zero-shot system achieves an end-to-end F1 score of 58.3%, with LLMs outperforming specialized event extraction models such as GoLLIE. For entity linking, ZEST achieves an F1 score of 45.7%, significantly surpassing OneNet, a state-of-the-art zero-shot baseline that achieves only 23.7%. However, these zero-shot results lag behind the best supervised systems by 20.1% and 37.0% in the end-to-end and AEL tasks, respectively, highlighting the need for further research.