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: |
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
Rose/grammatical_analysis/natural_language_processing_tools/text_preprocessing/pos_tagger/POS_tagger_nltk.py
Line 41 in 7cca46c