What is `max_seq_length`? about bert-ner

[kamalkraj]

Hi @sbmaruf
Currently model is trained to predict only NER tags for sequence length of 128 tokens, you can input sentence length more than 128, but output won't be good. The reason why i say it won't be good is ,BERT have positional embeddings, so after fine tuning only first 128 positions are fine tuned for NER task even though bert can accept maximum sequence length of 512.

In train set only 1 sentence has sequence length greater than 128 tokens. 2,4 in dev and test respectively .

[sbmaruf]

Thanks for the reply.