PyThaiNLP v4.1.0-beta1

Schedule

• First Beta release: 24 July 2023

Docs: https://pythainlp.github.io/dev-docs/
Report bug: https://github.com/PyThaiNLP/pythainlp/issues

Install: pip install --pre pythanlp

See 4.1 Milestone.

What is new?

Deprecation and other API changes

• 5e97e7c Change the default NER to thainer-v2

New API

• Add pythainlp.coref: Add pythainlp.coref for support Thai Coreference resolution #802
• Add wtpsplit to sentence segmentation & paragraph segmentation #804 and add paragraph_threshold into paragraph_tokenize function #806
• Add word approximation to pythainlp.soundex.sound by @wannaphong in #809
• Add pythainlp.wsd for Thai Word Sense Disambiguation by @wannaphong in #818
• Add pythainlp.chat and WangChanGLM to pythainlp.generate by @wannaphong in #819
• Add a param-free classification model (pythainlp.cls) by @c4n in #821
• Add pythainlp.el by @wannaphong in #822
• Add pythainlp.util.abbreviation_to_full_text #826 by @wannaphong in #826

Tokenizer

• Add wtpsplit engine to sentence_tokenize #804
• New paragraph_tokenize funtion to split Thai text to a paragraph. #804
• add paragraph_threshold into paragraph_tokenize function by @pavaris-pm in #806

Translate

• Add small100 to pythainlp.translate by @wannaphong in #815

Corpus

• Add orst list by @wannaphong in #810
• Add thai_synonym #825 by @wannaphong in #825

Util

• Add pythainlp.util.encoding by @wannaphong in #813
• Add pythainlp.util.spell_words by @wannaphong in #817
• Add pythainlp.util.abbreviation_to_full_text #826 by @wannaphong in #826

New Contributors

• @pavaris-pm made their first contribution in #806
• @falukelo made their first contribution in #824

Full Changelog: v4.0.0...v4.1.0-beta1