A Multimodal Text- and Graph-Based Approach for Open-Domain Event Extraction from Documents
2026-04-23 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors explain that understanding events from text is important but current methods either focus on limited event types or don’t fully use powerful language models. They point out that large language models often miss out on important document-level details because of technical constraints. To fix this, the authors created MODEE, which combines language model information with graph-based learning to better understand events across many types. Tests show that MODEE works better than previous methods and can also handle specific event types effectively.
Event ExtractionLarge Language Models (LLMs)Open-Domain Event ExtractionClosed-Domain Event ExtractionGraph-Based LearningDocument-Level ReasoningAttention DilutionLost-in-the-Middle PhenomenonMultimodal Learning
Authors
Praval Sharma
Abstract
Event extraction is essential for event understanding and analysis. It supports tasks such as document summarization and decision-making in emergency scenarios. However, existing event extraction approaches have limitations: (1) closed-domain algorithms are restricted to predefined event types and thus rarely generalize to unseen types and (2) open-domain event extraction algorithms, capable of handling unconstrained event types, have largely overlooked the potential of large language models (LLMs) despite their advanced abilities. Additionally, they do not explicitly model document-level contextual, structural, and semantic reasoning, which are crucial for effective event extraction but remain challenging for LLMs due to lost-in-the-middle phenomenon and attention dilution. To address these limitations, we propose multimodal open-domain event extraction, MODEE , a novel approach for open-domain event extraction that combines graph-based learning with text-based representation from LLMs to model document-level reasoning. Empirical evaluations on large datasets demonstrate that MODEE outperforms state-of-the-art open-domain event extraction approaches and can be generalized to closed-domain event extraction, where it outperforms existing algorithms.