[Py3.5] RegexpParser를 위한 Chunking Rule 테스트

/*******************************************************************************************************************
-- Title : [Py3.5] RegexpParser를 위한 Chunking Rule 테스트
-- Reference : 웹검색
-- Key word : nltk pos word_tokenize pos_tag chunk chunking 자연어처리 자연어 처리 pos tagging pos_tagging
                  토크나이저 word tokenize  청킹 tokenizing 
*******************************************************************************************************************/

■ Chunk Rule 테스트

# -*- coding: utf-8 -*-
 
from nltk.tokenize import sent_tokenize, word_tokenize
from nltk.tag import pos_tag
from nltk.chunk import RegexpParser
 
# ------------------------------
# -- word token & pos tagging
# ------------------------------
#sent = "Systems and methods for spectrally dispersed illumination optical coherence tomography."
#sent = "Telemetric docking station"
sent = "Hand-held medical-data capture-device having a digital infrared sensor with no analog readout ports and" \
       "optical detection of vital signs through variation amplification and interoperation with electronic medical record systems."
#sent = "Device for use in electro-biological signal measurement in the presence of a magnetic field."
 
word_token = word_tokenize(sent)
pos_tags = pos_tag(word_token)
 
print (sent)
print("... raw_text", "." * 100, "\n")
print (word_token)
print("... word_token", "." * 100, "\n")
 
 
# ------------------------------
# -- chunking
# ------------------------------
chunk_rule = r""" 
NP: {<N.*><JJ><NN>*}
    {<N.*><VBG><NN>*}
    {<J.*>*<NN>*}
"""
chunk_parse = RegexpParser(chunk_rule)
 
chunk = chunk_parse.parse(pos_tags)
print(chunk)
chunk.draw()
print(",,, chunk", "," * 100, "\n")
 
# ------------------------------
# -- 정규식 설명
# ------------------------------
"""
<RB.?>* = "0 or more of any tense of adverb," followed by:
<VB.?>* = "0 or more of any tense of verb," followed by:
<NNP>+ = "One or more proper nouns," followed by
<NN>? = "zero or one singular noun."

NP: {<N.*>*<Suffix>?}   # Noun phrase
VP: {<V.*>*}            # Verb phrase
AP: {<A.*>*}            # Adjective phrase

  {<DT|JJ>}          # chunk determiners and adjectives
  }<[\.VI].*>+{      # chink any tag beginning with V, I, or .
  <.*>}{<DT>         # split a chunk at a determiner
  <DT|JJ>{}<NN.*>    # merge chunk ending with det/adj
                     # with one starting with a noun
                     
parser = RegexpParser('''
... NP: {<DT>? <JJ>* <NN>*} # NP
... P: {<IN>}           # Preposition
... V: {<V.*>}          # Verb
... PP: {<P> <NP>}      # PP -> P NP
... VP: {<V> <NP|PP>*}  # VP -> V (NP|PP)*
... ''')

{<N.*>} # 명사(N으로 시작)인 모든 경우 
{<P.*>} # 대명사(P로 시작)인 모든 경우
{<DT><JJR>}  # DT와 JJR이 붙어 있는 경우
{<DT><J.*>}  # DT와 J로 시작하는 단어가 붙어 있는 경우 
{<DT><JJ>?<NN>} # <DT>와 <NN>사이에 <JJ>가 있든 없든..
"""