Skip to content

Problem converting the TIGER corpus into pickle format #10

@EineTasseKaffee

Description

@EineTasseKaffee

Hello there, I am relatively new to programming in general and language processing in particular, so please excuse if this seems like a silly problem:

After installing germalemma using pip, downloading the TIGER corpus in the CONLL09 format and also installing Pyphen, I am struggeling to covert the TIGER corpus into pickle format. (I used the anaconda prompt for all of this, which seemed useful as I use Jupyter Notebooks to code)

When I apply the code specified in the readme document, I get this error:
"python: can't open file 'germalemma/init.py': [Errno 2] No such file or directory"

I suspect I might have made a mistake with a detail a more experienced person would find too obvious to specify in the document?
Any help, suggestion or hint would be greatly appreciated! Thank you.
(Maybe there is even a more detailed tutorial on using germalemma somewhere? So far I haven't found anything)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions