PyThaiNLP v2.3.1 Released!

· April 5, 2021

PyThaiNLP v2.3.1 is This release is a bug fix release of PyThaiNLP 2.3.

Bug Fixed

Documentation: Report bug:

You can install or upgrade using pip install -U pythainlp

See PyThaiNLP 2.3 change log #445

Deprecation and other API changes

  • NER change a ThaiNER model (from ThaiNER 1.4 to ThaiNER 1.5). If you need use ThaiNER 1.4 model, You can use version in ThaiNameTagger class. pythainlp.tag.named_entity.ThaiNameTagger(version: str = '1.4') (Docs:


  • #484 Add: model option for attacut.tokenize()
  • #502 Add: corpus.util.revise_wordset() to revise tokenization dictionary
  • #503 Add: NERCut tokenization engine


  • License change:
  • #449 Fix: remove instances with [ or ] from etcc.txt
  • #467 Add: corpus.common.provinces() can now return romanized names
  • #476 Add: thai_family_names() to get a set of Thai family names
  • #487 Fix: thailand_provinces_th.csv not found issue
  • #492 Fix: remove erroneous AITT tag from ORCHID to UD table – thanks @c4n for the fix

POS Tagger

  • #464 Add: LST20 language model for part-of-speech tagging
  • #468 Add: port PerceptronTagger from NTLK. POS tagging no longer needs NLTK for dependency.
  • #478 Update: ORCHID POS tags documentation

Name Entity Tagging

  • #526 Update ThaiNER 1.4 to ThaiNER 1.5
  • #538 Add ThaiNameTagger version and add ThaiNER 1.4 support


  • #485 Fixed Romanize failed in some examples
  • #511 Add Thai W2P (Thai Word-to-Phoneme converter)

Text Summarize

  • #523 Add mT5 text summarize to pythainlp.summarize

Chunk parser

  • #524 Add pythainlp.tag.chunk


  • #481 Fix: remove_repeat_vowels() bug that remove spaces between different vowels
  • #483 Add: add remove() method to remove a word from a trie – thanks @korakot
  • #490 Fix: thai_strftime() - normalize output for unsupported directive (running in glibc and musl should produce the same output)
  • #512 Add: emoji_to_thai() to convert emoji to Thai description – thanks @ppirch for the development
  • #513 Add: thai_keyboard_dist() to calculate euclidean distance between two characters according to their location on a Thai keyboard layout – thanks @ppirch for the development

Thanks all the contributors. (Image made with contributors-img)

We build Thai NLP.


Twitter, Facebook