Property Modelling for Product Ontology using Vector Embeddings driven by LLMs and OCR

Lectures 21. march | Property Modelling for Product Ontology using Vector Embeddings driven by LLMS and OCR 2. February, 2024 Nikhil Acharya PoolParty Summit Identifying entities and relationships from heterogeneous data sources in the context of technical documentation is an important part of building a knowledge database. Technical data consists of tables, raw texts and images for various products. We use pre-trained LLM and OCR models to identify products and product attributes from these sources.