Skip to content

Links to the implementations of neural conversational models for different frameworks

Notifications You must be signed in to change notification settings

nicolas-ivanov/seq2seq_chatbot_links

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 

Repository files navigation

seq2seq chatbot links

Links to the implementations of neural conversational models for different frameworks. Contributions are welcomed.


Theano, Lasagne

A dialog system that is able to express emotions in a text conversation. See online demo.

Sample results for neutral emotions:

hi                                → hey you
how are you ?                     → i ' m fine , what about you ?
how old are you ?                 → i ' m 16 , how old are you ?
are you a leader or a follower ?  → i ' m a man who is a politician .
my name is david . what is my name ?    → i love your name .
is the sky blue or black ?        → the sky is blue
you love anime .                  → i ' m not a weeb

Tensorflow

Nice results:

Hi			            	→ Hi.
What is your name ?			→ Laura.
What does that mean ?		→ I dunno.
How old are you ?			→ thirty-five.
Who is Laura ?				→ My brother.
Say 'goodbye'				→ Alright.
Two plus two				→ manny...

Modified code of machine translation model. No answering randomisation is implemented in this code, so the models answers with the same phrase way each time:

hello baby					→ hello
how old are you ?			→ twenty .
i am lonely					→ i am not
nice						→ you ' re not going to be okay .
so rude						→ i ' m sorry .
are you a robot or human?	→ no .
are you better than siri?	→ yes .

Torch

Source code for a bunch of super nice articles by Jiwei Li - one of my favorite researches in the domain of neural conversational systems. Worth checking out.

tell me ... how long have you had this falling sickness ?   → a few months, I guess .
so i had the doctors test sammy ’s response to conditioning .   → so he took the pills .
what are you going to do ?  → i ’m going to get you a new car .
they fear your power your intellect .   → i ’m not afraid of your power .
Hello?					→ Hi.
How are you?			→ I'm fine.
What's your name?		→ It's hard to describe.
How so?					→ I'm not sure.
What color is the sky?	→ It's blue.
What is your job?		→ It's not that i'm a fucking werewolf!

Keras

The most popular implementation of Seq2seq architecture on GitHub. However, there is still no evidence of getting good results with this repo.

A wrapper for farizrahman4u/seq2seq used for running experiments. No good results were achieved so far.

Need to check this up.

A new generative chatbot whose training converges in few epochs, including a model pre-trained on a small but consistent dataset collected from dialogues of English courses online.

user: Hello! How are you?
computer:  i am fine , ok , well , thank you  .    (with probability of 0.540239)
user: What's your name?
computer:  janet .     (with probability of 0.319482)
user:  What do you like to do now?
computer:  let me think a minute .     (with probability of 0.286760)
user: I want to chat about computer science.
computer:  i am glad to hear there .     (with probability of 0.293063)
user: Are you a real girl or a computer program?
computer:  i am self employed . i would love to be well .     (with probability of 0.026870)
user: Why don't you look for a job?
computer:  i do not know . i am the bank .     (with probability of 0.053494)
user: So, you don't need a job!
computer:  no . i have to make a lot of money .     (with probability of 0.001279)

Corpora

A great overview of existing conversational datasets.

Get a lot of raw movie subtitles (~1.2Gb)

~ 40Mb after clearing out the technical data.

Papers

Refer to this great review by Richard Krisztian Csaky: Chatbot and Related Research Paper Notes with Images

as well as to his report paper in pdf: Deep Learning Based Chatbot Models

About

Links to the implementations of neural conversational models for different frameworks

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published