Event Argument Extraction with Enriched Prompts
This work addresses event argument extraction for natural language processing, but it appears incremental as it builds on existing prompt-based methods without introducing a new paradigm.
The paper tackles event argument extraction by exploring how enriching prompts with trigger, role arguments, and cross-event information affects performance, achieving unspecified improvements and demonstrating optimization potential in training objectives across small and large language models on the RAMS dataset.
This work aims to delve deeper into prompt-based event argument extraction (EAE) models. We explore the impact of incorporating various types of information into the prompt on model performance, including trigger, other role arguments for the same event, and role arguments across multiple events within the same document. Further, we provide the best possible performance that the prompt-based EAE model can attain and demonstrate such models can be further optimized from the perspective of the training objective. Experiments are carried out on three small language models and two large language models in RAMS.