This system generates text in a chosen language by taking in specific pieces of meaning, called semantic items. It figures out the type of sentences and parts of sentences needed, then looks up appropriate words and their features from a stored set of rules. Finally, it builds phrases, turns them into expressions, and arranges these expressions sequentially to form the complete text.
Why it matters: Filed before large language models (LLMs) became widely available. The complex rule-based generation described, which required extensive manual definition in 2017, could now be significantly simplified or even automated by LLM capabilities.
AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.
Reinvent this with AI