Lifecycle Management of DBpedia Neural QA Models - GSoC2021

Description
This project will consist of automating the process of DBpedia Neural Question Answering [1] model lifecycle management with the following tasks:
(1) make DBNQA models based on current dataset available to users;
(2) implement an evaluation service for DBpedia model evaluation with IRBench [2];
(3) integrate automatic build when changes occur in the DBpedia NSPM training dataset.

[1] https://github.com/AKSW/DBNQA
[2] https://github.com/AKSW/irbench

Goal
Create a Nerual Model Management Framework

Impact
Facilitate Neural Model life-cycle managing (updates, editions, issues) on new and old DBpedia versions.

Warm-up tasks
(1) Fork the NsPM project (https://github.com/AKSW/NSPM );
(2) Train the Monument 300 and Monument 600 datasets https://github.com/AKSW/NSpM/tree/master/data;
(3) Fork the KBox project (https://github.com/AKSW/KBox );
(4) Instantiate one of the datasets available in KBox.

Reference Material

  • “An example of an excellent proposal that was accepted a few years ago. Please mind that the number of total project hours have changed from 300 to 175.” Tommaso Soru

Mentors
Edgard Marx
Lahiru Hinguruduwa

Keywords
#NSpM #DBpedia #ModelManagement #AI #AIManagement #AILifecycle

1 Like

Hi @emarx. I’m really interested in this project. I’m a final year Software Engineering undergraduate at IIT- Sri Lanka. I have great knowledge and experience with Deep Learning and NLP. Hope I’m not too late to contact the mentor and start warm-up tasks. Looking forward to work on this project

thanks for your contact, it is not too late, good luck :slight_smile:

1 Like

Hi @emarx , My name is E Liu, i’m a junior at Northwest Normal University, China.I am very interested in these projects.I started warm-up tasks. I’m trying to understand all the details of the whole project and hope it’s not too late.Looking forward to your guidance.

Great, looking forward too :slight_smile:

I will be hosting a GSOC session next Friday, write down your questions and join me if you can.

Topic: Edgard Marx’s Zoom Meeting
Time: Apr 2, 2021 06:00 PM Amsterdam, Berlin, Rome, Stockholm, Vienna

Join Zoom Meeting

Zoom Video

Join our Cloud HD Video Meeting

Zoom is the leader in modern enterprise video communications, with an easy, reliable cloud platform for video and audio conferencing, chat, and webinars across mobile, desktop, and room systems. Zoom Rooms is the original software-based conference…

Meeting ID: 971 7701 8759
Passcode: dbpedia
One tap mobile
+16468769923,97177018759# US (New York)
+16699006833,97177018759# US (San Jose)

Dial by your location
+1 646 876 9923 US (New York)
+1 669 900 6833 US (San Jose)
+1 253 215 8782 US (Tacoma)
+1 301 715 8592 US (Washington DC)
+1 312 626 6799 US (Chicago)
+1 346 248 7799 US (Houston)
+1 408 638 0968 US (San Jose)
Meeting ID: 971 7701 8759
Find your local number: https://eccenca.zoom.us/u/adeQxEg4QS

1 Like

thanks for the awesome information.

Hi everyone. This will be my final blog of GSoC’21, and this blog will discuss how I’ve achieved the lifecycle management of the DBpedia neural QA model and how to use this latest feature. Basically, this blog will cover the latest features of bpm counter and how to use those features properly.