Desire100 / ChatBot-Implementation-with-TensorFlow-Framework

Cornell movie corpus data set contains more than 600 movies containing thousands of conversations between lots of characters.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ChatBot-with-TensorFlow-

In this project I used Cornell movie corpus data set which has more than 600 movies containing thousands of conversations between lots of characters. we will train our chatbot on this data set because we want to build a general chat bot that can have a general converstion with people. instead of soecified chat bit this is used for some specific purpose. the model that we will use can be trained on other datasets for some other purposes. for example will be abke to train the same chat bot on a more specific dataset like a calendar assistant or navigation assistant.

The implementation of this chatbot is divided in five parts, you can check out the code for each part for more understanding

1. PART ONE:

DATA PREPROCESSING:

This part involves different steps like importing of libraries, importing of data and cleanining. for more information about cleaning this data you can check out my repo named cleaning Cornell movie dataset.

2. PART TWO - BUILDING A SEQ2SEQ MODEL:

In this part we built the archetecture of our seq2seq model by using tensorflow library.

About

Cornell movie corpus data set contains more than 600 movies containing thousands of conversations between lots of characters.


Languages

Language:Python 58.6%Language:Jupyter Notebook 41.4%