Demo Application for LETO: Learning Engine Through Ontologies

Abstract

The massive amount of multi-formatted information available on the Web necessitates the design of software systems that leverage this information to obtain knowledge that is valid and useful. The main challenge is to discover relevant information and continuously update, enrich and integrate knowledge from various sources of structured and unstructured data. This paper presents the Learning Engine Through Ontologies (LETO) framework, an architecture for the continuous and incremental discovery of knowledge from multiple sources of unstructured and structured data. We justify the main design decision behind LETO's architecture and evaluate the framework's feasibility using the Internet Movie Data Base (IMDB) and Twitter as a practical application.

Multi3Generation: Multitask, Multilingual, and Multimodal Language Generation

“…In the same level, COMmonsEnse Transformers (COMET) 28 can generate new knowledge by adding new commonsense nodes of existing commonsense knowledge graphs like ConceptNet and ATOMIC 29 Retrieval Augmented Generation (RAG) 30 uses BART transformer-based model for NLG tasks using an extra intermediate step by adding external knowledge with Dense Passage Retrieval (DPR) 31 . LETO 32 is a system of GPLSI lab in Alicante that collects knowledge and creates a Knowledge Graph (KG) with external knowledge from structured and unstructured text where commonsense knowledge could give added value. The outcome of this research line, framed within WG2, but having also tight connections to WG1 and WG4, could be listed as follows:…”