-
Notifications
You must be signed in to change notification settings - Fork 31
Description
The new version seems not to have documentation on training new models. Following the old version's documentation to train lemmatizer/tagger/parser crashes due to Parser-v2 not being available.
Is there a new way to train models that does not require this component (if yes, which scripts should I run?), or am I supposed to add Parser-v2 from the old version to this one manually?
File "/projappl/clarin/test-tnpp/TNPP/train/train_models.py", line 176, in
create_model_directory(args)
File "/projappl/clarin/test-tnpp/TNPP/train/train_models.py", line 34, in create_model_directory
process_morpho(args) # train/dev files for tagger/parser
File "/projappl/clarin/test-tnpp/TNPP/train/train_models.py", line 68, in process_morpho
spec.loader.exec_module(morphotransfer)
File "", line 846, in exec_module
File "", line 982, in get_code
File "", line 1039, in get_data
FileNotFoundError: [Errno 2] No such file or directory: '/projappl/clarin/test-tnpp/Turku-neural-parser-pipeline/train/../Parser-v2/nparser/scripts/transfer_morpho.py'