Exploring In-Context Learning for Frame-Semantic Parsing
This provides a practical alternative to fine-tuning for domain-specific Frame-Semantic Parsing tasks, such as analyzing violent events, though it is incremental as it applies existing ICL methods to a new domain.
The paper tackled Frame-Semantic Parsing by using In-Context Learning with Large Language Models to avoid fine-tuning, achieving competitive F1 scores of 94.3% for Frame Identification and 77.4% for Frame Semantic Role Labeling on a subset of violent event frames.
Frame Semantic Parsing (FSP) entails identifying predicates and labeling their arguments according to Frame Semantics. This paper investigates the use of In-Context Learning (ICL) with Large Language Models (LLMs) to perform FSP without model fine-tuning. We propose a method that automatically generates task-specific prompts for the Frame Identification (FI) and Frame Semantic Role Labeling (FSRL) subtasks, relying solely on the FrameNet database. These prompts, constructed from frame definitions and annotated examples, are used to guide six different LLMs. Experiments are conducted on a subset of frames related to violent events. The method achieves competitive results, with F1 scores of 94.3% for FI and 77.4% for FSRL. The findings suggest that ICL offers a practical and effective alternative to traditional fine-tuning for domain-specific FSP tasks.