I got a terrible result when I use the lstm_crf code to do ner task based on BERT model, so did you?

guillaumegenthial / tf_ner

Simple and Efficient Tensorflow implementations of NER models with tf.estimator and tf.data

Apache License 2.0

923 stars 275 forks source link

I got a terrible result when I use the lstm_crf code to do ner task based on BERT model, so did you? #32

Open cedar33 opened 5 years ago

cedar33 commented 5 years ago

I got a terrible result when I use the lstm_crf code to do ner task based on BERT model, the loss stoped at 20 when batchsize=32, max_sequence_len=50 and num_tags=5, however when I use another code based on the same theory, it worked well. the main difference is that code use basic lstmcell, I can not understand. could you help me? by the way, I have trained the dataset use your lstm_crf code , it worked well.

**update I have soved this problem, thank you

guillaumegenthial commented 5 years ago

@cedar33 , Glad to know you solved your problem, if you have time to post more details here, I am sure other people will appreciate!