A Neural QA Model for DBpedia

With booming amount of information being continuously added to the internet, organising the facts becomes a very difficult task. Currently DBpedia hosts billions of such data points and corresponding relations in the RDF format.

RDF is a directed, labeled graph data format for representing information in the Web. SPARQL is a query language for RDF. SPARQL can be used to express queries across diverse data sources, whether the data is stored natively as RDF or viewed as RDF via middleware. The results of SPARQL queries can be results sets or RDF graphs. (Source : https://www.w3.org/TR/rdf-sparql-query/​) Extracting data from such data sources requires a query to be made in SPARQL and the response to the query is a link that contains the information pertaining to the answer or the answer itself.

Accessing such data is difficult for a lay user, who does not know how to write a query. This proposal tries to built upon a System :(​ https://github.com/AKSW/NSpM/tree/master ​) — which tries to make this humongous linked data available to a larger user base in their natural languages(now restricted to English) by improving, adding and amending upon the existing codebase.

The primary objective of the project being able to translate any natural language question to a valid SPARQL query.

Table containing information about the posts:

Serial Number Heading Abstract Published On Stage Number
1 The Selection Day My proposal was accepted for GSoC this year. A brief overview of my experience. 8th May 2019 Zero
2 Week Two Community Bonding Period | First Meeting 19th May 2019 Zero
3 Week Three Community Bonding Period | Literature Survey 30th May 2019 Zero
4 Stage 0 Report Community Bonding Period | Stage Completition Report 30th May 2019 Zero
5 Week Four&Five Stage 1 & 2| The Coding Begins 11th June 2019 One & Two
6 Week Six Stage 3 | Code Crusade Week 22nd June 2019 Three
7 Week Seven Stage 3 | Looking Beyond 25th June 2019 Three
8 Week Eight&Nine Stage 4 | Hard Week, Slow performance gains 9th July 2019 Four
9 Week Ten&Eleven Stage 5 | Attention 23rd July 2019 Five
10 Week Twelve&Thirteen Stage 6 | Grid Search 12th August 2019 Six
11 Week Forteen&Fiteen Stage 7 | The Results 23rd August 2019 Seven
12 Final Report Stage 7 | Final Report 23rd August 2019 Seven