Simple Thai Wordcut in Python using Maximum Matching

Thai Wordcut, wordcut
pip install pythaiwordcut==0.1.15


pythaiwordcut - Thai Wordcut in Python

A simple Thai wordcut written in Python, based on Maximum Matching algorithm by S. Manabu . Uses Lexitron (by NECTEC) dictionary as default

Please note: This project is under development and should not be use in production , all function and interface are subject to change. If you have issue or suggestion please feel free to ask, contribution is also very welcome :)


pip install pythaiwordcut


git clone
python install


import pythaiwordcut as pwt

pt = pwt.wordcut(removeRepeat=True, stopDictionary="<full path to txt file>", removeSpaces=True, minLength=1, stopNumber=False, removeNonCharacter=False, caseSensitive=True, ngram=(1, 2), negation=False)
print "|".join(pt.segment(u'ทดสอบการตัดคำ'))
  • removeRepeat: remove intention insertion spelling error such as (สบายยยยยย)
  • stopDictionary: remove word that exist in this specify text file (one word one line)
  • removeSpaces: remove blank space
  • minLength: minimum length of each word
  • stopNumber: remove number if exist
  • removeNonCharacter: remove character that are not Thai or English character
  • caseSensitive: if set to false, will remove stop word without regarding the case
  • ngram: Add word ngram from (1, 2)
  • negation: If set to true, then it will add NOT_ to every word after negation word and space