bb-ai.net

KARaML

KARaML is an acronym standing for Knowledge Assimilation using Reasoning and Machine Learning and refers to a methodology for deriving information from natural language text using a combination of symbolic Knolwedge Representation techniques and Machine Learning based technologies (such as language models). The KARaML Network is a group of collaborating researchers working in Artificial Intelligence and related disciplines, who are interested in exploring and applying this methodology. The nework holds semi-regular online meetings, shares software tools and other resources and sometimes collaborates on writing papers.

Resources and Information

KARaML Tools. A resource that enables direct online access (via Colab) to some software modules that implment functionality that may be useful for exploring Natural Language Understanding.
The paper introducing the KARaML Methodology:
Hong, Bennett, Clymo, Alvarez (2022) KARaML: Integrating Knowledge-Based and Machine Learning Approaches to Solve the Winograd Schema Challenge, AAAI-MAKE Spring Symposium. [Download]
Brandon's MkDocs info pages on Natural Language Understanding
Useful Links relating to Language Understanding and KRR/ML Hybrid approaches.
This is a Colab document maintained by collaborators. You can find more links to our resources and also to a lot of other sites on topics related to our interests.