Error running about discopy HOT 3 CLOSED

You cannot, unfortunately, select individual components of a stored pipeline easily. However, you could adjust the config.json file of the corresponding model to include only the connective component (just remove the other entries that follow).

For data preparation, I recommend using discopy-data in combination with the parser as follows (I guess the interface changed over the last days):

1. traditional feature-based parser: discopy-tokenize -i examples/wsj_0336 | discopy-add-parses -c | discopy-parse lin models/lin
2. neural parser: discopy-tokenize --tokenize-only -i examples/wsj_0336 | discopy-nn-parse bert-base-cased models/pipeline-bert-2

You could also first process your documents, store them in a single file and then parse this file by either parser pipeline:

1. discopy-tokenize -i examples/wsj_0336 | discopy-add-parses -c > dataset.json
2. discopy-tokenize -i examples/wsj_034X | discopy-add-parses -c >> dataset.json
3. discopy-nn-parse bert-base-cased models/pipeline-bert-2 -i dataset.json

Note: discopy-tokenize splits text files into multiple documents by three or more consecutive newlines (r'\n\n\n+')

from discopy.

You cannot, unfortunately, select individual components of a stored pipeline easily. However, you could adjust the config.json file of the corresponding model to include only the connective component (just remove the other entries that follow).

For data preparation, I recommend using discopy-data in combination with the parser as follows (I guess the interface changed over the last days):

1. traditional feature-based parser: discopy-tokenize -i examples/wsj_0336 | discopy-add-parses -c | discopy-parse lin models/lin
2. neural parser: discopy-tokenize --tokenize-only -i examples/wsj_0336 | discopy-nn-parse bert-base-cased models/pipeline-bert-2

You could also first process your documents, store them in a single file and then parse this file by either parser pipeline:

1. discopy-tokenize -i examples/wsj_0336 | discopy-add-parses -c > dataset.json
2. discopy-tokenize -i examples/wsj_034X | discopy-add-parses -c >> dataset.json
3. discopy-nn-parse bert-base-cased models/pipeline-bert-2 -i dataset.json

Note: discopy-tokenize splits text files into multiple documents by three or more consecutive newlines (r'\n\n\n+')

Thanks for your response. I have been able to run first two steps successfully. However, this repository doesn't contain 'models' folder, as well as config files. Can you please upload those too?

from discopy.

To not blow up the repository with models' histories, I put them under releases:
https://github.com/rknaebel/discopy/releases

from discopy.