Unable to reproduce extraction results about webke

[gijshendriksen]

@redreamality, a quick bump on this. Do you have a moment to take a look at this error?

[redreamality]

It looks like a problem with overlong sequence, which should have been correctly handled in our encoding layer. could you pls conda list your environment?

[gijshendriksen]

Thanks for having a look! I'm not using Conda, I'm just running it in a fresh Python 3.7 Docker container. To setup all required packages, I executed:

pip install bert4keras==0.10.0 tensorflow==2.2.0 beautifulsoup4 tqdm

pip freeze gives me the following list of installed packages:

absl-py==1.0.0
astunparse==1.6.3
beautifulsoup4==4.10.0
bert4keras==0.10.0
cachetools==4.2.4
certifi==2021.10.8
charset-normalizer==2.0.12
gast==0.3.3
google-auth==1.35.0
google-auth-oauthlib==0.4.6
google-pasta==0.2.0
grpcio==1.44.0
h5py==2.10.0
idna==3.3
importlib-metadata==4.11.3
Keras==2.3.1
Keras-Applications==1.0.8
Keras-Preprocessing==1.1.2
Markdown==3.3.6
numpy==1.21.5
oauthlib==3.2.0
opt-einsum==3.3.0
protobuf==3.20.0
pyasn1==0.4.8
pyasn1-modules==0.2.8
PyYAML==6.0
requests==2.27.1
requests-oauthlib==1.3.1
rsa==4.8
scipy==1.4.1
six==1.16.0
soupsieve==2.3.2
tensorboard==2.2.2
tensorboard-plugin-wit==1.8.1
tensorflow==2.2.0
tensorflow-estimator==2.2.0
termcolor==1.1.0
tqdm==4.64.0
typing-extensions==4.1.1
urllib3==1.26.9
Werkzeug==2.1.1
wrapt==1.14.0
zipp==3.8.0

Hope that helps!

[redreamality]

Since this repo has not been fully tested on CPUs, I'm not hundred percent sure about your problem.
However, based on your error loggings, I believe that this is a problem caused by eager of tensorflow.
You might wanna have a look at this link.
I'll close this issue because it is more likely a debugging issue in a different environment rather than discussing on the parper itself. Feel free to re-open it if you are still having problems regarding the paper.

[gijshendriksen]

Switching to a GPU-enabled machine solved the problem for me. I had no idea these issues could arise if running on CPU instead of GPU. Thanks for your help, much appreciated!