[Most-ai-contest] 使用NER資訊的Performance
張光瑜
simonc於iis.sinica.edu.tw
Thu 3月 26 09:37:15 CST 2020
Dear all,
在這裡先和大家道歉,我之前在報告時用的不用任何額外feature的model的performance數據是用舊版dataset得到的;和現在最新版的有點差距。結果其實是,用NER的feature會有明顯比較好的performance。
附加檔案是新的performance資料。
抱歉這成大家麻煩。
Regards,
張光瑜
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.iis.sinica.edu.tw/pipermail/most-ai-contest/attachments/20200326/fe413879/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: ner_feature_update_KuangYuChang_20200325_V1.pptx
Type: application/vnd.openxmlformats-officedocument.presentationml.presentation
Size: 57156 bytes
Desc: not available
URL: <http://www.iis.sinica.edu.tw/pipermail/most-ai-contest/attachments/20200326/fe413879/attachment-0001.bin>
More information about the Most-ai-contest
mailing list