Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Issue 60 spacy entity overlap #61

Open
wants to merge 4 commits into
base: master
Choose a base branch
from

Conversation

burgersmoke
Copy link
Contributor

This is an initial fix for what @soldni and I have discussed with spacy and overlapping entity spans. We may want to add additional match data later in an extension (i.e. the "underscore") but this works around an error for now.

#60

…spacy pipeline. This can be used as an entity matcher for UMLS concepts in other modular spacy pipelines. This is already being used in an operational capacity for syndromic surveillance.
…n QuickUMLS and SpacyQuickUMLS. Fixed keyword arguments to QuickUMLS when creating a spacy component. Added documentation as well. Removing previous standalone example Python file and instead adding an example of a QuickUMLS spacy pipleline to the README.
…t add entity spans which overlap on a token. Also added some documentation to the class and README.
@burgersmoke burgersmoke closed this Sep 3, 2020
@burgersmoke burgersmoke reopened this Sep 3, 2020
@burgersmoke
Copy link
Contributor Author

burgersmoke commented Sep 3, 2020

Sorry for the close/reopen but I was confused why this shows 4 commits instead of 1. The overall diff looks right, but please advise if there's a better way I should do this so that only the 1 commit (0dda67b) appears here.

@soldni
Copy link
Member

soldni commented Sep 30, 2020

Hey @burgersmoke,

Just a quick note to let you know that I've seen this PR, but I don't quite have the bandwidth at the moment to look at it closely.... hoping to come back to it over the upcoming weekend at the latest!

-Luca

@burgersmoke
Copy link
Contributor Author

That sounds great @soldni. I understand the limitations of bandwidth since I initially planned to submit these pull requests back in October 2019 and then lots of things got in my way.

@burgersmoke
Copy link
Contributor Author

Any update on this pull request? And perhaps bumping the version number in PyPi?

We're about to do a major release of medspacy (https://github.com/medspacy/medspacy) and we wanted to include QuickUMLS in our default pipeline if we could.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants