Source code for nltk.tag.mapping

# Natural Language Toolkit: Tagset Mapping
# Copyright (C) 2001-2017 NLTK Project
# Author: Nathan Schneider <>
#         Steven Bird <>
# URL: <>
# For license information, see LICENSE.TXT

Interface for converting POS tags from various treebanks
to the universal tagset of Petrov, Das, & McDonald.

The tagset consists of the following 12 coarse tags:

VERB - verbs (all tenses and modes)
NOUN - nouns (common and proper)
PRON - pronouns
ADJ - adjectives
ADV - adverbs
ADP - adpositions (prepositions and postpositions)
CONJ - conjunctions
DET - determiners
NUM - cardinal numbers
PRT - particles or other function words
X - other: foreign words, typos, abbreviations
. - punctuation

@see: and


from __future__ import print_function, unicode_literals, division
from collections import defaultdict
from os.path import join

from import load

_UNIVERSAL_DATA = "taggers/universal_tagset"

# _MAPPINGS = defaultdict(lambda: defaultdict(dict))
# the mapping between tagset T1 and T2 returns UNK if appied to an unrecognized tag
_MAPPINGS = defaultdict(lambda: defaultdict(lambda: defaultdict(lambda: 'UNK')))

def _load_universal_map(fileid):
    contents = load(join(_UNIVERSAL_DATA, fileid+'.map'), format="text")

    # When mapping to the Universal Tagset,
    # map unknown inputs to 'X' not 'UNK'
    _MAPPINGS[fileid]['universal'].default_factory = lambda: 'X'

    for line in contents.splitlines():
        line = line.strip()
        if line == '':
        fine, coarse = line.split('\t')

        assert coarse in _UNIVERSAL_TAGS, 'Unexpected coarse tag: {}'.format(coarse)
        assert fine not in _MAPPINGS[fileid]['universal'], 'Multiple entries for original tag: {}'.format(fine)

        _MAPPINGS[fileid]['universal'][fine] = coarse

[docs]def tagset_mapping(source, target): """ Retrieve the mapping dictionary between tagsets. >>> tagset_mapping('ru-rnc', 'universal') == {'!': '.', 'A': 'ADJ', 'C': 'CONJ', 'AD': 'ADV',\ 'NN': 'NOUN', 'VG': 'VERB', 'COMP': 'CONJ', 'NC': 'NUM', 'VP': 'VERB', 'P': 'ADP',\ 'IJ': 'X', 'V': 'VERB', 'Z': 'X', 'VI': 'VERB', 'YES_NO_SENT': 'X', 'PTCL': 'PRT'} True """ if source not in _MAPPINGS or target not in _MAPPINGS[source]: if target == 'universal': _load_universal_map(source) return _MAPPINGS[source][target]
[docs]def map_tag(source, target, source_tag): """ Maps the tag from the source tagset to the target tagset. >>> map_tag('en-ptb', 'universal', 'VBZ') 'VERB' >>> map_tag('en-ptb', 'universal', 'VBP') 'VERB' >>> map_tag('en-ptb', 'universal', '``') '.' """ # we need a systematic approach to naming if target == 'universal': if source == 'wsj': source = 'en-ptb' if source == 'brown': source = 'en-brown' return tagset_mapping(source, target)[source_tag]