WOAH: Preliminaries to Zero-shot Ontology Learning for Conversational Agents
This addresses the need for efficient ontology learning in conversational agent development, though it appears incremental as it builds on existing zero-shot and dependency-based methods.
The paper tackles the problem of ontology estimation for conversational agents by introducing the Weighted Ontology Approximation Heuristic (WOAH), a zero-shot approach that extracts verbs and nouns from data using dependencies, similarity, and sparsity metrics to generate a configurable ontology estimation.
The present paper presents the Weighted Ontology Approximation Heuristic (WOAH), a novel zero-shot approach to ontology estimation for conversational agents development environments. This methodology extracts verbs and nouns separately from data by distilling the dependencies obtained and applying similarity and sparsity metrics to generate an ontology estimation configurable in terms of the level of generalization.