Skip to content

Wang-Han/krr-question-answering

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

krr-question-answering

This project solves the tasks proposed by "Towards ai-complete question answering : a set of prerequisite toy tasks" by Jase et. al. from Facebook AI Research. Data set is under data/ folder.

The approach used is to parse the text using a lisp file (main.lsp) and to use Companions reasoning system to answer queries.

Team

Danilo Neves Ribeiro ([email protected]), Han Wang ([email protected])

Supervised by Prof. Ken Forbus, Northwestern University, IL, US

Report

Requirements

The following software is required to run this project:

1 - Common Lisp 2 - Northwestern University Companions software

How to run

    • First open companions and start a a new session.
    • The following must be loaded in order in Companions: 2.1 - base.meld -Defines global micro-theory and define base predicate and relations 2.2 - rules.meld - Defines the rules for reasoning about time, space and basic logic
    • In main.lsp change the variable "file-root" to the root directory of this project. Then go to Companions console and load main.lsp using the command (load "YOUR_FOLDER_DIRECTORY\main.lsp")
    • Check the output files generated in the data\ folder.

NOTE: Running the on full data might take quite some time. We recommend removing part of the data set beforehand.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Common Lisp 95.5%
  • Python 4.5%