-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Can't reproduce SRL result with allennlp==1.0.0 #4392
Comments
Possibly related to #4216 |
I guess there are some problems with pytorch_transformer and transformer lib. |
I saw in #4457 that the BERT SRL model is trained again. I evaluated it with Command
|
By changing the indexer in the dataset reader from |
Thanks! I will test it asap |
System (please complete the following information):
OS: Ubuntu 18.04.3 LTS
Python version: 3.7
AllenNLP version: v1.0.0
PyTorch version: 1.5
Allennlp-models: v1.0.0
Question
Hi @DeNeutoy , I try to reproduce the results on the OntoNotes dataset (conll 2012) in the Shi et al., 2019 paper used in the SRL demo. However, I could only get F1 around 0.79.
Command I used:
I also tried to train the model with config file in allennlp-models but only get to F1=79.
I found a related issue #4220 and was able to reproduce the result (86.5) with allennlp==0.9 and an old checkpoint https://s3-us-west-2.amazonaws.com/allennlp/models/bert-base-srl-2019.06.17.tar.gz. But I guess it might be worth reporting the issue since 1.0 is a stable version now.
Any help would be appreciated!
The text was updated successfully, but these errors were encountered: