You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Dec 16, 2022. It is now read-only.
The results from the online demo version of Open IE is different from the results I get when calling the model from python code, even it is using the exact same model stated on the demo page (openie-model.2020.03.26.tar.gz).
For example, the sentence "Yellowstone National Park is in the United States of America." yields the following results when using the online demo:
[ARG1: Yellowstone National Park] [V: is] [ARG2: in the United States of America.]
while calling the model from the code yields no results. Anyone can shed some light on why this might be?
The text was updated successfully, but these errors were encountered:
@Tharu87 Thank you for pointing this out. The issue is caused by the latest update to SpacyTokenizer, which tags auxiliary verbs like "is" as AUX instead of VERB. This should be resolved by this fix.
The results from the online demo version of Open IE is different from the results I get when calling the model from python code, even it is using the exact same model stated on the demo page (openie-model.2020.03.26.tar.gz).
For example, the sentence "Yellowstone National Park is in the United States of America." yields the following results when using the online demo:
[ARG1: Yellowstone National Park] [V: is] [ARG2: in the United States of America.]
while calling the model from the code yields no results. Anyone can shed some light on why this might be?
The text was updated successfully, but these errors were encountered: