INCATools / INCATools/ubergraph

Add text embedding vectors

Open
#168 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Makefile
Stars
53
Forks
6
PR merge metrics
No merged PRs in 30d

Description

This would be an alternative to informationContent for calculating semantic distance between two terms

Note that OLS now has vector embeddings, I think most of UG is in OLS, so could harvest from there, also use the same cache strategy as James
https://github.com/cthoyt/ols-client/issues/9

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the existing informationContent calculation and review the OLS vector-embeddings work referenced in cthoyt/ols-client#9. Compare the available OLS coverage with UG, then determine the cache strategy mentioned in the issue. Done means semantic distance between two terms can use text embedding vectors as an alternative to informationContent.

Written by the indexing model from the issue text.

Assessment

Domain
data, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.