https://github.com/Jerryzhao-z/simple-question-answering-with-memory-networks

Replication of results for the Large-Scale Simple Question Answering With Memory Networks article
https://github.com/Jerryzhao-z/simple-question-answering-with-memory-networks

Last synced: 3 months ago
JSON representation

Replication of results for the Large-Scale Simple Question Answering With Memory Networks article

• Host: GitHub
• URL: https://github.com/Jerryzhao-z/simple-question-answering-with-memory-networks
• Owner: Jerryzhao-z
• License: mit
• Created: 2017-02-26T13:41:08.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2016-05-17T16:32:28.000Z (over 8 years ago)
• Last Synced: 2024-06-29T06:35:05.096Z (4 months ago)
• Language: Python
• Size: 5.86 KB
• Stars: 12
• Watchers: 2
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-kbqa - [code

README

        
# Large-scale Simple Question Answering with Memory Network

## Installation

Create the `SETTINGS.json` file in the root of the project containing settings from the `SETTINGS.json.example`.

One have to specify location of all datasets and other local configuration information.

## Preprocessing

Objects in the Freebase dataset are separated by a whitespace and are located in the 3rd column of those files.

Both the `f(y)` and the list of available freebase entities is prepared by the `preprocessing/freebase.py` script.

The vocabulary of individual words is produced with the `preprocessing/vocabulary.py` script.

Questions preprocessing `g(q)` is done with the `preprocessing/questions.py` script.