PyThaiNLP 3.1 change log

[wannaphong]

Schedule

• First development release: 31 August 2022
• Beta release: 20 September 2022
• Production release: 24 September 2022

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 Add pythainlp.parse.dependency_parsing #706

Name Entity Tagging

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

Transliteration

• Add ISO 11940 transliteration #659 Add ISO 11940 transliteration
• Add Thai W2P v0.2 and PyThaiNLP v3.0.6dev0 #660 Add Thai W2P v0.2
• Add wunsen #686 Add wunsen
• Wunsen Mandarin and Japanese update #694 Wunsen Mandarin and Japanese update

PyThaiNLP Corpus downloader

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

Text normalization

• Normalise Lakkhangyao #673 Add a normalising rule for Lakkhangyao ๅ

Translate

• add gpu option #674 add gpu option

Text summarize

• Add mt5 cpe kmutt thai sentence sum #679 Add mt5 cpe kmutt thai sentence sum

Util

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

Soundex

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

Other

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