Trustworthy NLP systems must be rule and knowledge based given all statistical systems like large language models, machine learning, and neural networks are not. With the advent of large language models that can be queried about common knowledge, it is natural to use them to generate linguistic and world knowledge that can be leveraged by the NLP++ framework.
Building a Feature Rich English Dictionary with LLMs
David describes building a new feature-rich English dictionary using the local LLM Ollama on his machine and how you can help. Here are two videos. The first an overview, the second a “how to help” use your computer to process almost a half a million words.
VisualText and Copilot
David de Hilster talks about how Copilot is already helping create trustworthy knowledge in the NLP++ ecosystem.
