# -*- coding: utf-8 -*-
from typing import List, Tuple
[docs]def pos_tag(
words: List[str],
engine: str = "perceptron",
corpus: str = "orchid"
) -> List[Tuple[str, str]]:
"""
Marks words with part-of-speech (POS) tags, such as 'NOUN' and 'VERB'.
:param list words: a list of tokenized words
:param str engine:
* *perceptron* - perceptron tagger (default)
* *unigram* - unigram tagger
* *wangchanberta* - wangchanberta model (support lst20 corpus only \
and it supports a string only. if you input a list of word, \
it will convert list word to a string.
* *tltk* - TLTK: Thai Language Toolkit (support TNC corpus only.\
if you choose other corpus, It's change to TNC corpus.)
:param str corpus: the corpus that used to create the language model for tagger
* *lst20* - `LST20 <https://aiforthai.in.th/corpus.php>`_ corpus \
by National Electronics and Computer Technology Center, Thailand \
It is free for **non-commercial uses and research only**. \
You can read at \
`Facebook <https://www.facebook.com/dancearmy/posts/10157641945708284>`_.
* *lst20_ud* - LST20 text, with tags mapped to Universal POS tag \
from `Universal Dependencies <https://universaldependencies.org/>`
* *orchid* - `ORCHID \
<https://www.academia.edu/9127599/Thai_Treebank>`_ corpus, \
text from Thai academic articles (default)
* *orchid_ud* - ORCHID text, with tags mapped to Universal POS tags
* *pud* - `Parallel Universal Dependencies (PUD)\
<https://github.com/UniversalDependencies/UD_Thai-PUD>`_ \
treebanks, natively use Universal POS tags
* *tnc* - Thai National Corpus (support tltk engine only)
:return: a list of tuples (word, POS tag)
:rtype: list[tuple[str, str]]
:Example:
Tag words with corpus `orchid` (default)::
from pythainlp.tag import pos_tag
words = ['ฉัน','มี','ชีวิต','รอด','ใน','อาคาร','หลบภัย','ของ', \\
'นายก', 'เชอร์ชิล']
pos_tag(words)
# output:
# [('ฉัน', 'PPRS'), ('มี', 'VSTA'), ('ชีวิต', 'NCMN'), ('รอด', 'NCMN'),
# ('ใน', 'RPRE'), ('อาคาร', 'NCMN'), ('หลบภัย', 'NCMN'),
# ('ของ', 'RPRE'), ('นายก', 'NCMN'), ('เชอร์ชิล', 'NCMN')]
Tag words with corpus `orchid_ud`::
from pythainlp.tag import pos_tag
words = ['ฉัน','มี','ชีวิต','รอด','ใน','อาคาร','หลบภัย','ของ', \\
'นายก', 'เชอร์ชิล']
pos_tag(words, corpus='orchid_ud')
# output:
# [('ฉัน', 'PROPN'), ('มี', 'VERB'), ('ชีวิต', 'NOUN'),
# ('รอด', 'NOUN'), ('ใน', 'ADP'), ('อาคาร', 'NOUN'),
# ('หลบภัย', 'NOUN'), ('ของ', 'ADP'), ('นายก', 'NOUN'),
# ('เชอร์ชิล', 'NOUN')]
Tag words with corpus `pud`::
from pythainlp.tag import pos_tag
words = ['ฉัน','มี','ชีวิต','รอด','ใน','อาคาร','หลบภัย','ของ', \\
'นายก', 'เชอร์ชิล']
pos_tag(words, corpus='pud')
# [('ฉัน', 'PRON'), ('มี', 'VERB'), ('ชีวิต', 'NOUN'), ('รอด', 'VERB'),
# ('ใน', 'ADP'), ('อาคาร', 'NOUN'), ('หลบภัย', 'NOUN'),
# ('ของ', 'ADP'), ('นายก', 'NOUN'), ('เชอร์ชิล', 'PROPN')]
Tag words with different engines including *perceptron* and *unigram*::
from pythainlp.tag import pos_tag
words = ['เก้าอี้','มี','จำนวน','ขา', ' ', '=', '3']
pos_tag(words, engine='perceptron', corpus='orchid')
# output:
# [('เก้าอี้', 'NCMN'), ('มี', 'VSTA'), ('จำนวน', 'NCMN'),
# ('ขา', 'NCMN'), (' ', 'PUNC'),
# ('=', 'PUNC'), ('3', 'NCNM')]
pos_tag(words, engine='unigram', corpus='pud')
# output:
# [('เก้าอี้', None), ('มี', 'VERB'), ('จำนวน', 'NOUN'), ('ขา', None),
# ('<space>', None), ('<equal>', None), ('3', 'NUM')]
"""
if not words:
return []
_support_corpus = ["lst20", "lst20_ud", "orchid", "orchid_ud", "pud"]
if engine == "perceptron" and corpus in _support_corpus:
from pythainlp.tag.perceptron import tag as tag_
elif engine == "wangchanberta" and corpus == "lst20":
from pythainlp.wangchanberta.postag import pos_tag as tag_
words = ''.join(words)
elif engine == "tltk":
from pythainlp.tag.tltk import pos_tag as tag_
corpus = "tnc"
elif engine == "unigram" and corpus in _support_corpus: # default
from pythainlp.tag.unigram import tag as tag_
else:
raise ValueError(
"pos_tag not support {0} engine or {1} corpus.".format(
engine,
corpus
)
)
word_tags = tag_(words, corpus=corpus)
return word_tags
[docs]def pos_tag_sents(
sentences: List[List[str]],
engine: str = "perceptron",
corpus: str = "orchid",
) -> List[List[Tuple[str, str]]]:
"""
Marks sentences with part-of-speech (POS) tags.
:param list sentences: a list of lists of tokenized words
:param str engine:
* *perceptron* - perceptron tagger (default)
* *unigram* - unigram tagger
* *wangchanberta* - wangchanberta model (support lst20 corpus only)
* *tltk* - TLTK: Thai Language Toolkit (support TNC corpus only.\
if you choose other corpus, It's change to TNC corpus.)
:param str corpus: the corpus that used to create the language model for tagger
* *lst20* - `LST20 <https://aiforthai.in.th/corpus.php>`_ corpus \
by National Electronics and Computer Technology Center, Thailand
* *lst20_ud* - LST20 text, with tags mapped to Universal POS tags \
from `Universal Dependencies <https://universaldependencies.org/>`
* *orchid* - `ORCHID \
<https://www.academia.edu/9127599/Thai_Treebank>`_ corpus, \
text from Thai academic articles (default)
* *orchid_ud* - ORCHID text, with tags mapped to Universal POS tags
* *pud* - `Parallel Universal Dependencies (PUD)\
<https://github.com/UniversalDependencies/UD_Thai-PUD>`_ \
treebanks, natively use Universal POS tags
* *tnc* - Thai National Corpus (support tltk engine only)
:return: a list of lists of tuples (word, POS tag)
:rtype: list[list[tuple[str, str]]]
:Example:
Labels POS for two sentences::
from pythainlp.tag import pos_tag_sents
sentences = [['เก้าอี้','มี','3','ขา'], \\
['นก', 'บิน', 'กลับ', 'รัง']]
pos_tag_sents(sentences, corpus='pud)
# output:
# [[('เก้าอี้', 'PROPN'), ('มี', 'VERB'), ('3', 'NUM'),
# ('ขา', 'NOUN')], [('นก', 'NOUN'), ('บิน', 'VERB'),
# ('กลับ', 'VERB'), ('รัง', 'NOUN')]]
"""
if not sentences:
return []
return [pos_tag(sent, engine=engine, corpus=corpus) for sent in sentences]