Re:Estimating the probabilities of causation via deep monoto...
by wwarner on Monday September 13, 2021 @11:56AM
(#28513080)
One application I can think of would be to dialog systems. Tracing the meaning in a conversation between two strangers is determined by statements and responses, and the degree of unexpectedness of each utterance. Say a person asks a yes or no question, but gets a response along the lines of "I'm talking about X, not Y"; it would be useful to be able to go back and retrace the conversation at that point and try different responses in an effort understand what's being said.
[ Parent
| on HN ]
There are no comments on this comment yet.