"My favorite Gary Marcus quote", via Geoffrey Hinton:) http://www.cs.toronto.edu/~hinton/marcusquote.html …
-
-
Replying to @rsalakhu @ceobillionaire
He showed this at last week's Evolution of Deep Learning symposium as well. And then highlighted the date
1 reply 0 retweets 3 likes -
did he give an argument as to why he disagreed with the quote? from what I gather, Hinton thinks problem of understanding was solved by Google Translate. I think this is laughable; no current system can comprehend a children’s story.
2 replies 2 retweets 18 likes -
I am not nearly knowledgeable enough to comment on this. But I remember the argument being that while machine translation & language seem to be tasks better suited for symbolic AI, feature representations from DL without an explicit understanding of tasks still do well on them
1 reply 0 retweets 1 like -
machine translation and even Superglue are poor proxies for genuine comprehension the fact that large datasets have correlations with things doesn’t mean models like BERT can comprehend a narrative, medical report, or news article
3 replies 6 retweets 37 likes -
Replying to @GaryMarcus @sshkhr16 and
but thanks to
@sshkhr16 for clarifying what hinton’s argument might be, even though i am not convinced by it.1 reply 0 retweets 4 likes -
Replying to @GaryMarcus @sshkhr16 and
Problem is people are operating on different definitions of “comprehension”
1 reply 0 retweets 0 likes
i gave operational definition in reply to my own tweet: answering who what where when why how etc about a narrative or article
-
-
Replying to @GaryMarcus @sshkhr16 and
Obviously agree given our own long line of work on semantic frame based training of machine translation, and semantic frame based machine translation evaluation metrics (MEANT)
0 replies 0 retweets 0 likesThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.