snorkel-team / snorkel

A system for quickly generating training data with weak supervision
https://snorkel.org
Apache License 2.0
5.81k stars 857 forks source link

SwellShark implementation #1612

Closed YiranChe closed 3 years ago

YiranChe commented 4 years ago

Dear Snorkel Team, I saw on your issues that you implemented the SwellShark algorithm. I didn't find it in the documentation. I'm wondering whether you could tell me which function is SwellShark. Thank you so much!

jason-fries commented 4 years ago

Hi @YiranChe, We never released the original SwellShark code, but there is a newer paper that implements NER tagging using Snorkel. This paper removes the need to identify candidate entities a priori before training your labeling model and provides library code for autogenerating dictionary labeling functions from knowledge bases like the Unified medical Language System (UMLS). That repo will be public in the next 1-2 weeks.

Hope this helps! Happy to answer any other questions.

github-actions[bot] commented 3 years ago

This issue is stale because it has been open 90 days with no activity. Remove stale label or comment or this will be closed in 7 days.

rjurney commented 3 years ago

@jason-fries was this code you mention released?

sebpretzer commented 3 years ago

@jason-fries was this code you mention released?

I believe this is it: https://github.com/som-shahlab/trove