Lets Make a Question Answering chatbot using the bleeding edge in deep learning (Dynamic Memory Network). We'll go over different chatbot methodologies, then dive into how memory networks work, with accompanying code in Keras.
Code + Challenge for this video:
Nemanja's Winning Code:
Vishal's Runner up code:
Web app to run the code yourself:
Please subscribe! And like. And comment. That's what keeps me going.
More Learning resources:
Join us in the Wizards Slack channel:
And please support me on Patreon:
Follow me:
Twitter:
Facebook: Instagram: Instagram:
Signup for my newsletter for exciting updates in the field of AI:
Hit the Join button above to sign up to become a member of my channel for access to exclusive content!
imagine a chatbot that outputs Bash comands , comand line programs would get an interface more natural than GUI , without having to modify them ( note : non graphical Linux apps work on Windows ) also could i submit that for the coding challenge ?
I think that all Q&A problems are NLP tasks. NLP and linguistics are the foundations from which different levels of abstractions constructs more hard things like disambiguation (to answer factoid questions), translation (to understand or reformulate questions), etc…
Maybe, there are equivalent. But I don’t think so.
Great video and code btw! :):)
good thoughts and thanks!
One day, one day I will understand all of this.
LF Tang now after one year could you tell me how much did you understand?
LF Tang now after two years could you tell me how much did you understand?
Bro I was at your stage once
Glad I’m not alone
Did you understood it now, I don’t:(
I’m a beginner student of deep learning. So your videos help me a lot to understand this universe. Thanks.
np
siraj, have you considered doing more videos where you focus more on the machine learning itself, with just numpy? I love these practical application videos so much but it wouldn’t be a bad idea to go into a more detailed level.
yes Spark that is on my radar, youre reading my mind thanks
I didn’t know we can have explicit memory in an ANN. Awesome video! just as always it is!
thanks!
Great! Thanks for this, it’s right what I was looking for, I’ll give it a try
np
Hey Siraj
Is it possible to find the similarity of two sentences using Tensorflow? I mean, I would want the result to be a non binary value. Is there a link from where I could find more information about this? I have already looked at Denny Brtiz’s code for text classification. Thank you!
Cool thanks!
Vectorize using Sequence autoencoders. Then find cosine similarity.
Wouldn’t tf-idf be better? I haven’t worked with sequence autoencoders.
tf-idf is good when you have a huge corpus.
My corpus is pretty small. Could you please direct me to any python implementation of Sequence autoencoders? I am very new to this having no background.
Hello Siraj, and community, anyone know what would I have to change or tweak in this method for build a Q&A System in another language, other than English as shown? any ideas of pre-trained language models for Portuguese? Keep up the nice work Siraj, congrats! Cheers to all.
thanks! use portugese dataset
this is my submission for now, I am working on improving this a bit to be able to run on a much bigger dataset (hoping maybe I can use wikipidia articels
)
https://github.com/imdark/How_to_make_a_chatbot
Hi Siraj, thanks for the video! I checked out Nemanja’s Winning Code, but it actually can’t be implemented with tensorflow v1.0. I have raised my question in detail here, could you have a look and shed some light on how to fix it in the issue? Thanks
https://github.com/Nemzy/language-translation/issues/1
Hi Siraj, i had a question regarding the chatbot models……How do i combine a generative model with a retrieval based model??Generative model will be for training the network to learn the language and the retrieval model is for the purpose of retrieving domain knowledge. Can you suggest me something?
Things are happening so fast that he had to cover three different architectures in order to catch people up
Bro can you make a video tutorial on implementation of text summarisation using abstraction method😅
Imagine a real-time chatbot for game engines, used for RPGs.
Wow this was way more complicated than the typical video I’ve seen on your channel. I would need an hour long version of this to understand anything.
Man, I you are awesome! Thank you so much. Stay this much motivated everytime!
Qs after viewing (Notes about video shown below)
episodic module: what changes on each pass? if sent thru the same wouldn’t output be same?
Is the code he was showing in the video available to see? I didn’t see it on the github page
Notes on video
Dynamic Memory Network
types of memory; semantic (input txt), episodic (addtl info)
Gru cell replaces lstm cell; simplifies by only using two gates & no memory unit; update & reset
Create sequence (Glove) vectors from input text
Separate training data from testing data
Feed to input method that creates hidden states after each sentence
hidden states known as facts
?? matrix multiplication, biased term. gets into how to use the gru cell with updates and resets
trying to find if the current fact is relevant to the answer
output from input method feeds question module which processes input word by word
Q mod outputs vector using same gru and weights as input module
model created by replicating the hippa campus function in human brain
??
Attention function assigns 0 or 1 to each fact
multiple episodes are created; processes all facts x times
helps determine what info is relevant
but what changes on each pass? if sent thru the same wouldn’t output be same?
loss model cascading loops entropy. Discratic gradient ascent implementation (rmsprop)
sometimes its good to give the direct link for the resources specially datasets
#Siraj has this incredible way of blending Advanced Technical knowledge with humor. Awesome #Siraj. U r helping me understand and learn AI easily . Thanks a lot.