EPISODE · Jun 12, 2016 · 5 MIN
Build an AI Reader - Machine Learning for Hackers #7
from Siraj Raval
This video will get you up and running with your first AI Reader using Google's newly released pre-trained text parser, Parsey McParseface. The code for this video is here: https://github.com/llSourcell/AI_Reader I created a Slack channel for us, sign up here: https://wizards.herokuapp.com/ Here's the original blog post about Parsey: https://research.googleblog.com/2016/05/announcing-syntaxnet-worlds-most.html This is Google's repo for Parsey: https://github.com/tensorflow/models/tree/master/syntaxnet If you're interested in NLP, check out Michael Collins course. This guy is such a G (he co-authored Parsey), I took this class at Columbia and it was one of the few where I actually attended every session. (it's free and open source!): https://www.coursera.org/course/nlangp Link to API.AI in case you want to go that route: https://api.ai/ The political debate fact checker was an idea I had but never got around to building. It takes the transcript from a political debate, extracts the intent of a claim, queries it against google, perhaps scrapes some search result data and then assigns it a truthfulness rating out of 100. If it falls below a certain threshold, that person must be lying! How cool would that be? I love you guys! Thanks for watching my videos, I do it for you. I left my awesome job at Twilio and I'm doing this full time now. I recently created a Patreon page. If you like my videos, feel free to help support my effort here!: https://www.patreon.com/user?ty=h&u=3191693 Much more to come so please subscribe, like, and comment. Follow me: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
What this episode covers
This video will get you up and running with your first AI Reader using Google's newly released pre-trained text parser, Parsey McParseface. The code for this video is here: https://github.com/llSourcell/AI_Reader I created a Slack channel for us, sign up here: https://wizards.herokuapp.com/ Here's the original blog post about Parsey: https://research.googleblog.com/2016/05/announcing-syntaxnet-worlds-most.html This is Google's repo for Parsey: https://github.com/tensorflow/models/tree/master/syntaxnet If you're interested in NLP, check out Michael Collins course. This guy is such a G (he co-authored Parsey), I took this class at Columbia and it was one of the few where I actually attended every session. (it's free and open source!): https://www.coursera.org/course/nlangp Link to API.AI in case you want to go that route: https://api.ai/ The political debate fact checker was an idea I had but never got around to building. It takes the transcript from a political debate, extracts the intent of a claim, queries it against google, perhaps scrapes some search result data and then assigns it a truthfulness rating out of 100. If it falls below a certain threshold, that person must be lying! How cool would that be? I love you guys! Thanks for watching my videos, I do it for you. I left my awesome job at Twilio and I'm doing this full time now. I recently created a Patreon page. If you like my videos, feel free to help support my effort here!: https://www.patreon.com/user?ty=h&u=3191693 Much more to come so please subscribe, like, and comment. Follow me: Twitter: https://twitter.com/sirajraval Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
NOW PLAYING
Build an AI Reader - Machine Learning for Hackers #7
No transcript for this episode yet