Accenture / Accenture/AmpliGraph

Explicitly provide negative facts

Open
#208 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
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

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.