Skip to content

Possible improvement of tagging results #24

Open

Description

@Aliss55

Issue

The tagging results can be improved using the generate file or by trying wider regex patterns .

Examples

Current results = [[('La', 'UNK'), ('princesa', 'NOUN'), ('juega', 'UNK'), ('hoy', 'UNK')], [('El', 'UNK'), ('valiente', 'UNK'), ('caballero', 'UNK'), ('lucha', 'UNK'), ('contra', 'UNK'), ('el', 'UNK'), ('dragón', 'NOUN')]]

ExpectedResults=[ [('La', 'DET'), ('princesa', 'NOUN'), ('juega', 'VERB'), ('hoy', 'ADV')], [('El', 'DET'), ('valiente', 'ADJ'), ('caballero', 'NOUN'), ('lucha', 'VERB'), ('contra', 'ADP'), ('el', 'DET'), ('dragón', 'NOUN')] ]

Reference line

def tag_sentences_with_pos(self, tokenized_sentences: list) -> list:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Labels

No labels
No labels

Projects

No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions