AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How to Improve Predict Middle Sentence by Reading Left and Right Sentences
I like that a lot. So let's actually talk about some of these models that can do this kind of common sense reasoning that you've worked on. In particular, i think i've looked at two of them, delorian and comon. Why do they improve over existing pre trained language models to better perform common sense inference? Ye, so delorian is inference tam algoridm. It's not a mutian learning method, perse but more like, once you have learn nd model, especially language model, can you then use it off the shelf through a better agoritm so that the model can do things that originallythe model was not trained for.