pycorrector
pycorrector copied to clipboard
MacBERT等深度模型误纠解决思路
MacBERT等深度模型结合ngram规则纠错效果相对很好,但深度模型误纠比较高,请问有什么解决思路呢
1、模型优化:补充负例case(无错样本),把误纠的填进去; 2、专名过滤:人名、地名、专名等词加到 confusion dict,过滤处理; 3、输出macbert纠错置信度,只纠正高置信度错误。
1、模型优化:补充负例case(无错样本),把误纠的填进去; 2、专名过滤:人名、地名、专名等词加到 confusion dict,过滤处理; 3、输出macbert纠错置信度,只纠正高置信度错误。
macbert纠错置信度是怎么算的
softmax的概率值就是
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.(由于长期不活动,机器人自动关闭此问题,如果需要欢迎提问)