allenai / allenai/ontoemma

Result issues

Open
#22 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
73
Forks
13
PR merge metrics
No merged PRs in 30d

Description

Hi,
I 'm trying to reproduce your results, but It seems to contradict the results on your paper.
Firstly, how could you take an advantage of the external context information like definitions or Medline contexts which are not included in the code.
Secondly, the results of UMLS test set I reproduced are following.

P | R | F1 | Acc
-- | -- | -- | --
baseline(LR) | 0.9988 | 0.9567 | 0.9773 | 0.9855
NN+f+w+c | 0.9795 | 0.9569 | 0.9681 | 0.9786

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.