PyThaiNLP v3.1.0-beta0

This is the beta version for PyThaiNLP v3.1.

You can install by pip install --pre pythainlp==3.1.0b0.

Documentation: https://pythainlp.github.io/dev-docs/

Report bug: https://github.com/PyThaiNLP/pythainlp/issues

See PyThaiNLP 3.1 change log

See 3.1 Milestone.

What is new?

Deprecation and other API changes

#687 Remove deprecated function

• pythainlp.word_vector; doesnt_match, get_model, most_similar_cosmul, sentence_vectorizer, similarity. use WordVector class instead
• pythainlp.util.delete_tone. use pythainlp.util.remove_tonemark instead
• Remove pythainlp.util.time_time. use pythainlp.util.time_to_thaiword instead
• pythainlp.tokenize.syllable_tokenize. use pythainlp.tokenize.subword_tokenize instead

Dependency Parsing

• Now, PyThaiNLP support dependency_parsing 🎉 Add pythainlp.parse.dependency_parsing #706

Name Entity Tagging

• #665 Add Thai-NNER pythainlp.tag.NNER
• #658 Add LST20NER onnx model. It is LST20NER model to onnx model from fine-turning by WangchanBERTa model.

Transliteration

• #659 Add ISO 11940 transliteration
• #660 Add Thai W2P v0.2
• #686 Add wunsen
• #694 Wunsen Mandarin and Japanese update

PyThaiNLP Corpus downloader

• #656 Add support zip/tar.gz to download corpus

Text normalization

• #673 Add a normalising rule for Lakkhangyao ๅ

Translate

• #674 add gpu option

Text summarize

• #679 Add mt5 cpe kmutt thai sentence sum

Util

• #682 Add live-dead syllable classification
• #684 Add live dead syllable classify
• #690 Add tone detector

Soundex

• #699 Add Thai-English Cross-Language Transliterated Word Retrieval using Soundex Technique

Other

• #689 map NG tag to PART
• #691 Remove TinyDB as a dependency
• #692 Fix notifications that newer versions of corpora are available
• Add warning about LST20 license

What's Changed

• Add more words from Royal Society by @wannaphong in #653
• Add support zip/tar.gz to download corpus by @wannaphong in #656
• Update from dev by @wannaphong in #657
• Add ISO 11940 transliteration by @wannaphong in #659
• Add Thai W2P v0.2 and PyThaiNLP v3.0.6dev0 by @wannaphong in #660
• Add LST20NER onnx model by @wannaphong in #658
• Add Thai-NNER by @wannaphong in #665
• Update dev base from 3.0 base by @wannaphong in #668
• PyThaiNLP 3.0.7 by @wannaphong in #670
• Update dev branche from pythainlp-3.0 branche by @wannaphong in #672
• Normalise Lakkhangyao by @chameleonTK in #673
• add gpu option by @vikimark in #674
• Bump tensorflow from 2.5.3 to 2.6.4 by @dependabot in #677
• Bump tensorflow from 2.6.4 to 2.7.2 by @dependabot in #678
• Add mt5 cpe kmutt thai sentence sum by @wannaphong in #679
• Add live-dead syllable classification by @wannaphong in #682
• Fixed CI Bug by @wannaphong in #683
• Add live dead syllable classify by @wannaphong in #684
• Add wunsen by @wannaphong in #686
• Add ThaiSum sentence segmentor by @chameleonTK in #688
• map NG tag to PART by @chameleonTK in #689
• Add tone detector by @wannaphong in #690
• Remove deprecated function by @wannaphong in #687
• Remove TinyDB as a dependency by @BLKSerene in #691
• Fix notifications that newer versions of corpora are available by @BLKSerene in #692
• Start PyThaiNLP v3.1.0-dev0 by @wannaphong in #693
• Wunsen Mandarin and Japanese update by @cakimpei in #694
• Add Thai-English Cross-Language Transliterated Word Retrieval using Soundex Technique by @wannaphong in #699
• Fixed #700 by @wannaphong in #701
• Update add-word_detokenize from dev by @wannaphong in #703
• Add word_detokenize by @wannaphong in #697
• Move model by @wannaphong in #705
• Add pythainlp.parse.dependency_parsing by @wannaphong in #706

New Contributors

• @chameleonTK made their first contribution in #673
• @vikimark made their first contribution in #674
• @BLKSerene made their first contribution in #691
• @cakimpei made their first contribution in #694

Full Changelog: v3.0.9...v3.1.0-beta0

All Contributors

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

We build Thai NLP.

PyThaiNLP