KG3D Learning and Reasoning Webinar

by Simon Vandevelde

Operational decisions are an important part of knowledge-intensive organizations, as these are taken in a high volume on a daily basis. However, describing these decisions in a standardized format such as DMN is a time-consuming task, as various textual sources need to be analyzed. In this talk, we present the results of our experiments on an automated approach to generating decision tables from natural language based on the GPT-3 LLM. Through a total of 72 experiments over six problem descriptions, we evaluated GPT-3’s decision logic modeling and reasoning capabilities. While GPT-3 demonstrates promising abilities in extracting decision context and identifying relevant variables from natural language, further enhancements are needed to improve its decision table capabilities for efficient automation of DMN modeling.

by Ioannis Dasoulas

An abundance of tabular data exists and is used by a wide range of applications. However, a big portion of these data lack the semantic information necessary for users and machines to properly understand them. This lack of table semantic understanding impedes their usage in data analytics pipelines. Existing solutions are focused on specific annotation tasks and types of tables, and rely solely on large knowledge bases, making it difficult to re-use in real-world settings. In this talk, we present TorchicTab, a
versatile semantic table interpretation system able to annotate tables with varied structures by using either an external knowledge graph, such as Wikidata, or annotated tables with pre-defined terms for training. The results demonstrate TorchicTab’s ability to produce accurate annotations for different tasks across varied datasets.