This repository connects learning apps which have been developed by DHBW students as Open Source Projects.
The training data is a key common ressource which is used by most of those learning- and exploration apps.
Telegram Bot
Client Only Chatbot
Audio DHBW Chatbot (under construction)
Study Groups Competition App (under construction).
The Scientific Purpose Web Harvester supports you when it comes to literature research and gives you the chance to draft / generate question and answer pairs for a specific topic automatically. The SCP is also recommended in DHBW-Wissenschaftliche-Arbeiten. If you want to improve the SCP, you can find the repository here.
The quality of most of the mentioned DHBW Learning Apps is mainly influenced by the quality of the underlying training data.
Every lecturer is invited to
- Fork this repository
- Optimize the training data
- Raise a Pull Request to ensure the changes come back to this main DHBW training data repository
The plan is to have one training data file across several study paths to support interdisciplinary exploration and collaboration.
If there are however good reasons to split the information into several training data files (e.g. performance reasons reg. the NLP training...) we could also do so.
A holistic data adapter could transform trainingdata from and to the DHBW Learning Apps format (which is basically a list of question and answer pairs). This could be beneficial in order to improve the interoperability with other Open Source Learning Applications.
Maybe this could be a part of the lecture series for WWI20DSA - 'Web-Programmierung (15.11.2021 - 11.02.2022, 3. Semester).
Consider copying --> adding Lukas Blank's approach to https://github.com/fancy-flashcard/ffc-extended.