This article explains how ontology-based semantic layers work and advocates for their use as versatile enterprise tools. They add shared meaning, context, and governance to data, improving integration, analytics, oversight, and AI reliability across organizational systems.
We present an AI-assisted framework that uses LLMs to map unstructured organizational communications to a domain-specific metamodel and corresponding enterprise process activities. By linking messages to affected and dependent processes, the framework supports real-time situational awareness and proactive risk identification. Evaluation demonstrates effectiveness and scalability on large communication streams and process models.
This lesson introduces Wikidata and its underlying data structure. It shows how to navigate and query Wikidata using the Query Builder and SPARQL, and how its data model can be used to explore historical data.
We present a disjunctive Datalog encoding of the problem of query entailment over RDFS knowledge graphs under the metamodeling semantics.
This article examines an approach to formalizing the description of intelligent transportation systems (ITS) based on semantic modeling. Modern ITS architectures are analyzed, including the concept of cooperative intelligent transportation systems and the "vehicular cloud." Integration of the semantic model with the classification of user needs based on the KAREN methodology is proposed.
MIT affiliates engage with the MIT-IBM Computing Research Lab to bring rigorous theory to production systems.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.