CoderMusou
problem the result
dataset: msra The rest is configured according to the readme section, Why the result is not good? ^_^ please~
FitlogCallback evaluation on data-test:
SpanFPreRecMetric: f=0.536364, pre=0.553125, rec=0.520588
label_acc: acc=0.957234
Evaluation on dev at Epoch 27/100. Step:3429/12700:
SpanFPreRecMetric: f=0.536364, pre=0.553125, rec=0.520588
label_acc: acc=0.957234
Did you finish 100 epochs?
Yes, I finished 100 epochs. But the result of p ,r and f1 are more than 70%
Can you tell me how to get the structural components (radicals) of Chinese characters? Can you share them
Can you tell me how to get the structural components (radicals) of Chinese characters? Can you share them
The link is in readme, https://github.com/kfcd/chaizi
Yes, I finished 100 epochs. But the result of p ,r and f1 are more than 70%
Where is your dataset collected?
The data set I collected came from the original paper, and the source of the data set was mentioned in the original paper
------------------ 原始邮件 ------------------ 发件人: "CoderMusou/MECT4CNER" @.>; 发送时间: 2021年12月10日(星期五) 下午2:56 @.>; @.@.>; 主题: Re: [CoderMusou/MECT4CNER] problem the result (Issue #5)
Yes, I finished 100 epochs. But the result of p ,r and f1 are more than 70% Where is your dataset collected?
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.