nicolas-ivanov / Seq2seq_chatbot_links

seq2seq chatbot links

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

Theano, Lasagne

lukalabs/cakechat

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

Conchylicultor/DeepQA

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...

nicolas-ivanov/tf_seq2seq_chatbot

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

jiweil/Neural-Dialogue-Generation

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 .

macournoyer/neuralconvo

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

farizrahman4u/seq2seq

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

nicolas-ivanov/debug_seq2seq

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

codekansas/keras-language-modeling

Need to check this up.

oswaldoludwig/Seq2seq-Chatbot-for-Keras

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 Survey of Available Corpora for Building Data-Driven Dialogue Systems

A great overview of existing conversational datasets.

AlJohri/OpenSubtitles

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

Cornell Movie-Dialogs Corpus

~ 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