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.

Frame semantic parsing (Gildea and Jurafsky, 2002) is a natural language understanding (NLU) task involving finding structured semantic frames and their arguments from natural language text as formalized by the FrameNet project (Baker et al., 1998). Frame semantics has proved useful in understanding user intent from text, finding use in modern voice assistants (Chen et al., 2019), dialog systems (Chen et al., 2013), and even text analysis (Zhao et al., 2023). A semantic frame in FrameNet describes an event, relation, or situation and its participants. When a frame occurs in a sentence, there is typically a "trigger" word in the sentence which is said to evoke the frame. In addition, a frame contains a list of arguments known as frame elements which describe the semantic roles that pertain to the frame. A sample sentence parsed for frame and frame elements is shown in Figure 1. FrameNet provides a list of lexical units (LUs) for each frame, which are word senses with may evoke the frame when they occur in a sentence. For instance, the frame "Attack" has lexical units "ambush.n",

One of the common traits of past and present approaches for Semantic Role Labeling (SRL) is that they rely upon discrete labels drawn from a predefined linguistic inventory to classify predicate senses and their arguments. However, we argue this need not be the case. In this paper, we present an approach that leverages Definition Modeling to introduce a generalized formulation of SRL as the task of describing predicate-argument structures using natural language definitions instead of discrete labels. Our novel formulation takes a first step towards placing interpretability and flexibility foremost, and yet our experiments and analyses on PropBank-style and FrameNet-style, dependency-based and span-based SRL also demonstrate that a flexible model with an interpretable output does not necessarily come at the expense of performance. We release our software for research purposes at https://github.com/SapienzaNLP/dsrl.