search

ayyyq / TARA

code for [ACL23] An AMR-based Link Prediction Approach for Document-level Event Argument Extraction
19 stars 2 forks source link

environment setting #9

Open cejas233 opened 1 month ago

cejas233 commented 1 month ago

Thank you for sharing! However, the results I obtained on the RAMS dataset are lower than the paper. I am wondering if this could be due to virtual environment configuration issues. While running the script you provided, I encountered an error "TypeError: init() got an unexpected keyword argument 'label_smoothing'", which might be caused by a version mismatch in some package. Could you please provide me with details of your environment? ========for span F1======== dev

Precision: 40.9049 Recall: 50.4510 F1: 45.1792

test

Precision: 42.5606 Recall: 50.1748 F1: 46.0551 ========for head F1======== dev

Precision: 46.7093 Recall: 57.6099 F1: 51.5901

test

Precision: 49.3327 Recall: 58.1585 F1: 53.3833

ayyyq commented 1 month ago

Please see this issue for our environment setting. Thank you.

ayyyq commented 1 month ago

Also, please comment out these lines and uncomment these lines to calcuate Head F1 due to the inconsistent annotation of span boundaries.

cejas233 commented 6 days ago

Also, please comment out these lines and uncomment these lines to calcuate Head F1 due to the inconsistent annotation of span boundaries.

Thank you so much for your reply. Fpllow what you said, I got higher results than before. However, I still didn't get the results in your paper. Would you like to upload the results you get in rams? Thank you again.