KeySoft

parsing the same sentence with amrlib parser, for example, gives me this result with amr-unknown: ``` # ::snt Which architect of Marine Corps Air Station Kaneohe Bay was also tenant...

hi @ramon-astudillo, well, I was trying to follow your setup instructions from [here](https://github.com/IBM/transition-amr-parser) for setup and training (the default action-pointer network config `bash run/run_experiment.sh configs/amr2.0-action-pointer.sh` ). This is the code...

would mind sharing your trained checkpoint to see if it makes any difference?

Let me provide the full code as I made it based on your example. It gives me an error when I try to run it. ``` from lnn import (Predicate,...

the second example in your doc (complex reasoning example) has incomplete code. Can you please add full code there?

Hi @macabdul9, Thank you for the comments. Yes, it would really help if you could share the trained checkpoint. May I ask you to share it with me, please? Thanks.

@glicerico, thank you for the checkpoint. But as I understand, as per the @macabdul9 comment, I cannot use it without the "label dictionary", right? If you have that dictionary, maybe...

@glicerico, I've just created a new fork from yours. I made some changes to the code related to running on gpu. Also added annotations to the classes. And added evaluation...

@glicerico, thank you for your review. However my question was more about the eval() method of the DialogClassifier class. As you can see it doesn't use my annotated classes (act_label_names...

Sorry, but I don't see where you see the problem with the act_label_names. > to print incorrectly, as the classes in act_label_names are numbered differently from the predictions that is...