Adding External Knowledge and Controllability to Language Models with Megatron-CNTRL

Originally published at:

Large language models such as Megatron and GPT-3 are transforming AI. We are excited about applications that can take advantage of these models to create better conversational AI. One main problem that generative language models have in conversational AI applications is their lack of controllability and consistency with real-world facts. In this work, we try…

The next level of coversational AI - story generation with control keywords. What’s your next AI story about? Tell us how this paper will help you in your work.