Accenture / Accenture/AmpliGraph
Explicitly provide negative facts
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.2k
- Forks
- 257
- PR merge metrics
- No merged PRs in 30d
Description
In the current form, we can only provide true facts and Ampligraph generates negatives automatically. In many cases, though it is very common to be certain about facts that are false. It would be nice to be able to inform the model. In fact it might be easier if when providing ground truth to set a belief score next to the triplet. For example
nick friend Judy 0.7
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file or test entry point is named. Start by tracing how ground-truth triplets are accepted and how Ampligraph generates negative facts, then determine how explicit false facts or belief scores such as nick friend Judy 0.7 should be represented. Done would mean the requested input is supported with defined behavior for negative facts and belief scores.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100