dice-group / dice-group/embeddings.cc
Universal Recommender
Open
low-priority
- Dominant language
- Python
- Stars
- 3
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
If we have good embeddings for DBpeda or Wikidata, we could create a website for an "universal recommender system". Contents e.g.:
- Songs
- Bands
- Books
- Movies
- Animals
- Other categories from the respective ontologies
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the existing project and its support for embeddings from DBpedia or Wikidata. Define the recommender's scope, supported ontology categories, and website requirements; done would require an agreed implementation plan or a working universal recommender.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, web-dev
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100