Skip to content

Questions based on English Comprehension are usually asked to check the Reader's understanding about the comprehension. Our aim is to develop an automated supervised algorithm which can help the system to learn from the comprehension and use it to determine correct answer to the respective question.

Notifications You must be signed in to change notification settings

harsh-agar/Unseen-passage-QA-system

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Unseen-passage-QA-system

Questions based on English Comprehension are usually asked to check the Reader's understanding about the comprehension. Our aim is to develop an automated supervised algorithm which can help the system to learn from the comprehension and use it to determine correct answer to the respective question.

More details on this can be found on the following link: https://sites.google.com/iiitdmj.ac.in/cs615ml18/home

Install TensorFlow version 1.2+ in Python 3 Also make sure you’ve installed each of the following: Jupyter Numpy Matplotlib Optionally, you can install TQDM to view training progess and get training speed metrics, but it's not required.

Download the Stanford’s Global Vectors for Word Representation (GloVe) dataset from http://nlp.stanford.edu/data/glove.6B.zip and dtore in 'glove_zip_file'

Also download the Babi dataset from https://s3.amazonaws.com/text-datasets/babi_tasks_1-20_v1-2.tar.gz and store it in 'data_set_zip'

Now simply clone the provided repository and run the notebook 'QA - Test.ipynb'

About

Questions based on English Comprehension are usually asked to check the Reader's understanding about the comprehension. Our aim is to develop an automated supervised algorithm which can help the system to learn from the comprehension and use it to determine correct answer to the respective question.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •