Re:Natural language benchmarks don’t measure AI models’ gene...
by Animats on Monday August 24, 2020 @02:07AM
(#24257910)
That's useful for chatbots, where you have a big FAQ and people ask questions. That's exactly what RASA does, using TensorFlow. It's reasonably good at matching user questions with stored questions. But that's all the AI part does.
[ Parent
| on HN ]
There are no comments on this comment yet.