Enhancing Frame Detection with Retrieval Augmented Generation

TL;DR

This paper introduces RCIF, a novel retrieval-augmented generation method for frame detection that improves accuracy and robustness in extracting semantic frames from raw text, achieving state-of-the-art results on FrameNet datasets.

Contribution

RCIF is the first RAG-based approach for frame detection that operates without explicit target spans and demonstrates superior performance across various settings.

Findings

Achieves state-of-the-art on FrameNet 1.5 and 1.7.

Reduces task complexity by narrowing candidate search space.

Enhances generalization in translating questions to SPARQL.

Abstract

Recent advancements in Natural Language Processing have significantly improved the extraction of structured semantic representations from unstructured text, especially through Frame Semantic Role Labeling (FSRL). Despite this progress, the potential of Retrieval-Augmented Generation (RAG) models for frame detection remains under-explored. In this paper, we present the first RAG-based approach for frame detection called RCIF (Retrieve Candidates and Identify Frames). RCIF is also the first approach to operate without the need for explicit target span and comprises three main stages: (1) generation of frame embeddings from various representations ; (2) retrieval of candidate frames given an input text; and (3) identification of the most suitable frames. We conducted extensive experiments across multiple configurations, including zero-shot, few-shot, and fine-tuning settings. Our results show that our retrieval component significantly reduces the complexity of the task by narrowing the search space thus allowing the frame identifier to refine and complete the set of candidates. Our approach achieves state-of-the-art performance on FrameNet 1.5 and 1.7, demonstrating its robustness in scenarios where only raw text is provided. Furthermore, we leverage the structured representation obtained through this method as a proxy to enhance generalization across lexical variations in the task of translating natural language questions into SPARQL queries.