https://github.com/americast/qald

Question Answering over Linked Data
https://github.com/americast/qald

nlp scrapping sparql

Last synced: about 1 month ago
JSON representation

Question Answering over Linked Data

• Host: GitHub
• URL: https://github.com/americast/qald
• Owner: americast
• Created: 2018-09-26T09:45:59.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2019-01-01T17:21:19.000Z (almost 7 years ago)
• Last Synced: 2024-12-13T19:13:46.874Z (10 months ago)
• Topics: nlp, scrapping, sparql
• Language: Python
• Homepage:
• Size: 202 KB
• Stars: 2
• Watchers: 4
• Forks: 8
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Question Answering over Linked Data

## An attempt to build an automatic system to answer natural language queries

[![Gitter chat](https://badges.gitter.im/gitterHQ/gitter.png)](https://gitter.im/QALD/Lobby#)

The natural language queries are processed and transformed into SPARQL queries, which is used to lookup DBpedia to find a solution.

Install requirements using:  

`pip3 install -r req.txt`

Create a folder `data/` and place datasets there.  

Run the standalone implementation using `python3 Sparql.py "u"`.  

Otherwise, run the flask app using `python3 app.py` and answer interact from the frontend.

Sample dataset used can be found at https://github.com/ag-sc/QALD/blob/master/7/data/qald-7-train-largescale.json .

To open the front end, simply open `index.html` when inside the folder `qald-interface` from a browser.

A partial implementation which uses Blazegraph hosted over a local network is available under `kmst.py`.