Closed travellertea closed 6 years ago
Thank you for your question. My answers are as follows:
This model is based on Bidirectional LSTM-CRF.
This is trained by CoNLL2003 dataset.
Because the published model is trained by CoNLLL2003 all(train + valid + test) datasets.
In anaGo 1.0.0, I released new trained dataset. This is trained by CoNLL2003 train + valid datasets. I think it is comparable to some papers score.
with best regards
Hello There,
Question 1: url = 'https://storage.googleapis.com/chakki/datasets/public/models.zip' What is this model trained on for NER tagging?
Question 2: Why is the trained model performing significantly better with the trained model, compared to when I train a model with Conll2003 data and evaluate on the test set?
Cheers, TZ