Towards Acquiring Case Indexing Taxonomies From Text

Taxonomic case-based reasoning is a conversational casebased reasoning methodology that employs feature subsumption taxonomies for incremental case retrieval. Although this approach has several benefits over standard retrieval approaches, methods for automatically acquiring these taxonomies from text documents do not exist, which limits its widespread implementation. To accelerate and simplify feature acquisition and case indexing, we introduce FACIT, a domain independent framework that combines deep natural language processing techniques and generative lexicons to semi-automatically acquire case indexing taxonomies from text documents. FACIT employs a novel method to generate a logical form representation of text, and uses it to automatically extract and organize features. In contrast to standard information extraction approaches, FACIT’s knowledge extraction approach should be more accurate and robust to syntactic variations in text sources due to its use of logical forms. We detail FACIT and its implementation status.