[英]How to reduce loss and improve accuracy in text classification?
I am using following code to implement Intent Recognition with BERT using Keras and TensorFlow 2我正在使用以下代码使用 Keras 和 TensorFlow 2 使用 BERT 实现意图识别
My training dataset has around 250 intents, each intent having ~80 utterances associated to it.我的训练数据集有大约 250 个意图,每个意图都有大约 80 个与之相关的话语。 So total utterance is 20K所以总话语是20K
The base code works fine, however when I use my dataset, the accuracy drops to 1%基本代码工作正常,但是当我使用我的数据集时,准确率下降到 1%
Is this happening because the number of intents is huge?发生这种情况是因为意图的数量很大吗? If not, can you please suggest if optimisation needs to be modified in order to achieve accuracy in the model?如果没有,您能否建议是否需要修改优化以达到 model 的精度?
Thanks!谢谢!
This probably happened due to two reasons这可能是由于两个原因
Rohit罗希特
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.