NTCIR-13 MedWeb task: Evaluation results

-MedWeb Japanese subtask evaluation results: NTCIR-13_MedWeb_ja_results.xlsx
-MedWeb English subtask evaluation results: NTCIR-13_MedWeb_en_results.xlsx
-MedWeb Chinese subtask evaluation results: NTCIR-13_MedWeb_zh_results.xlsx

Run_ID corresponds to the file name of participant run results. 
Run_ID’s format is “[team ID]_medweb_result-[subtask (ja/en/zh)]-[counter ID (1-3)]”. 
Run results are evaluated by 8 metrics as follows: Exact match, F1 (micro), Precision (micro), Recall (micro), F1 (macro), Precision (macro), Recall (macro), and Hamming loss. 

For details, please refer to the MedWeb website (http://mednlp.jp/medweb/NTCIR-13/) and the “Overview of the NTCIR-13 MedWeb Task” in the NTCIR Online Proceedings.

Shoko Wakamiya, Mizuki Morita, Yoshinobu Kano, Tomoko Ohkuma, Eiji Aramaki, Overview of the NTCIR-13: MedWeb Task, In Proceedings of the 13th NTCIR Conference, 2017.