Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepText: Facebook's text understanding engine

code.facebook.com

Post reply on HN
Print view View original

81–90 of 142 posts

Re: DeepText: Facebook's text understanding engine

#81

Post by ylem »

zardeh wrote: post #72
astrange wrote: post #69

Earlier quoted context omitted.

Game AI uses minmax decisions, so it does simulate the opponent to pick _their_ best move, then it picks the move that removes their best options. That's why it's so unsportsmanlike when losing and why it doesn't go for points when winning. It doesn't have a specific profile of the opponent, though, instead it thinks they're another AlphaGo. That's an area they could work on.

AG doesn't actually use minimax, it uses montecarlo tree search, which doesn't even try to simulate a good opponent, it just plays lots of games very fast.

Actually, the cool thing about AG is that it doesn't just use MCTS, but that it adds in deep learning and reinforcement learning :-) I was surprised by how readable their paper was!

Here's a link: http://www.nature.com/nature/journal/v529/n7587/full/nature1...

I think you search on the title, you can find probably find a non paywalled version.

Re: DeepText: Facebook's text understanding engine

#82

Post by omarforgotpwd »

iamdave wrote: post #2

Slightly contrarian, or maybe not-but is anyone else sort of fatigued with social media trying it's hardest to do it all for you? Algorithmic timelines telling me what happened while I was gone (trust me, twitter...I would have gotten to it eventually), prioritizing what shows up (trust me facebook, I do a very good job hiding content on my own), telling me what I ought to buy (trust me, Amazon if I wanted it-I'd eit…

Nobody wants these features, but Facebook doesn't make them for the users. They make them for the advertisers / suppliers to increase sales.

Re: DeepText: Facebook's text understanding engine

#83

Post by gambler »

msie wrote: post #27
devindotcom wrote: post #15

Earlier quoted context omitted.

Heh yeah I wrote about this a while back - http://techcrunch.com/2013/01/27/facebooks-categorial-impera... But you add human intelligence to this kind of thing and it starts getting creepily accurate much of the time if you're looking to promote certain behaviors, expose others, or what have you.

On yesterday's episode of POI a character said that the Machine (an AI) has to contain a simulation of a person in order to understand what that person will do.

At highest level this is true. Any prediction must be based on some model, and that model can be considered a simulation of the subject.

Re: DeepText: Facebook's text understanding engine

#84

Post by DanielBMarkham »

renaudg wrote: post #79
DanielBMarkham wrote: post #22

Earlier quoted context omitted.

But that's not what they're doing. I'll get mentioned in a comment while I'm on the site. I'll click over and read the comment and reply to it. Then, once I'm away from the computer for 30-60 seconds or so (I'm sure they have a system training for this), I get the email notification -- even if the original back-and-forth occurred an hour ago. The timing of when I get the email has nothing at all to do with when the e…

This sounds like a bug / coincidence. I've never got a later email about something that happened live while I was browsing the site, and was already notified about.

A couple of times is a coincidence. I stopped counting after seven.

So you're saying that there's a bug. And the bug waits for me to stop using Facebook, then emails me things from Facebook.

I find this quite difficult to believe. At the least, it's a very convenient bug.

Re: DeepText: Facebook's text understanding engine

#85

Post by dennyabraham »

iamdave wrote: post #2

Slightly contrarian, or maybe not-but is anyone else sort of fatigued with social media trying it's hardest to do it all for you? Algorithmic timelines telling me what happened while I was gone (trust me, twitter...I would have gotten to it eventually), prioritizing what shows up (trust me facebook, I do a very good job hiding content on my own), telling me what I ought to buy (trust me, Amazon if I wanted it-I'd eit…

I wonder how well these decision systems stack against random suggestions? I notice it feels like I fixate on the few people or subjects that are regularly presented to me to the exclusion of everyone else.

Re: DeepText: Facebook's text understanding engine

#86

Post by daveguy »

duaneb wrote: post #10
gvurrdon wrote: post #4

Earlier quoted context omitted.

Recommendations, algorithmic timelines and so on are indeed a bit of a nuisance. Similarly, Google Now is annoying me a lot at the moment but I can't use my watch fully without turning it on.

I find Google Now to be far more useful than e.g. Facebook "recommendations", which are basically ads.

This pisses me off to no end. When I disable something like web browsing history because I get a nagging feeling that Google knows more about me than it should.

Then on the way out of work I try an "OK Google. Directions home"[0] to get a time estimate or best route estimate and it tells me I have to turn on browser history to continue or some other such bs. I wonder when Google Now will understand "Ok google. F?!k you Google."

[0] correction: that's more likely "ok Google. OK Google! OK GOOGLE! Damnit (click google now, click microphone). Directions home."

Re: DeepText: Facebook's text understanding engine

#87

Post by deet »

buskila wrote: post #30
Guildpact wrote: post #17

I wonder if this is in response to Google's open sourcing of Parsey McParseface: http://googleresearch.blogspot.com/2016/05/announcing-syntax...

Or Microsoft's language parser: https://www.microsoft.com/cognitive-services/en-us/language-...

Facebook already has Wit.ai which is extremely similar to Microsoft's LUIS, and in some ways more advanced.

Re: DeepText: Facebook's text understanding engine

#88

Post by deet »

Guildpact wrote: post #17

I wonder if this is in response to Google's open sourcing of Parsey McParseface: http://googleresearch.blogspot.com/2016/05/announcing-syntax...

If this post is a response to anything, it is most similar to Google's recently announced Allo, at least from a product perspective.

It's a little tough to figure out what Facebook's goal with the post was though since it's not very technical.

Re: DeepText: Facebook's text understanding engine

#89

Post by avs733 »

narrator wrote: post #7
iamdave wrote: post #2

Slightly contrarian, or maybe not-but is anyone else sort of fatigued with social media trying it's hardest to do it all for you? Algorithmic timelines telling me what happened while I was gone (trust me, twitter...I would have gotten to it eventually), prioritizing what shows up (trust me facebook, I do a very good job hiding content on my own), telling me what I ought to buy (trust me, Amazon if I wanted it-I'd eit…

When all you have is a machine learning classifier, everything looks like a classification problem.

and it becomes especially problematic when prediction becomes conflated with classification

Re: DeepText: Facebook's text understanding engine

#90

Post by dclowd9901 »

iamdave wrote: post #2

Slightly contrarian, or maybe not-but is anyone else sort of fatigued with social media trying it's hardest to do it all for you? Algorithmic timelines telling me what happened while I was gone (trust me, twitter...I would have gotten to it eventually), prioritizing what shows up (trust me facebook, I do a very good job hiding content on my own), telling me what I ought to buy (trust me, Amazon if I wanted it-I'd eit…

You also risk exposing yourself merely to an echo chamber as everything is automatically self reinforcing. This is bad stuff -- socially manipulative dark patterns.
Post reply on HN