himkt / konoha
๐ฟ An easy-to-use Japanese Text Processing tool, which makes it possible to switch tokenizers with small changes of code.
โ230Updated 6 months ago
Related projects โ
Alternatives and complementary repositories for konoha
- Python version of Sudachi, a Japanese tokenizer.โ391Updated 2 years ago
- A Japanese tokenizer based on recurrent neural networksโ388Updated 5 months ago
- A Cython MeCab wrapper for fast, pythonic Japanese tokenization and morphological analysis.โ402Updated last week
- Unidic packaged for installation via pip.โ79Updated last year
- Pure-Python Japanese character interconverter for Hiragana, Katakana, Hankaku, and Zenkakuโ315Updated 3 months ago
- Sentence boundary disambiguation tool for Japanese texts (ๆฅๆฌ่ชๆๅข็ๅคๅฎๅจ)โ186Updated 7 months ago
- A lexicon for Sudachiโ233Updated 3 weeks ago
- A comparison tool of Japanese tokenizersโ118Updated 5 months ago
- mecab-python. you can find original version here//taku910.github.io/mecab/โ539Updated 2 weeks ago
- Juman++ (a Morphological Analyzer Toolkit)โ380Updated last year
- ๐ A list of pre-trained BERT models for Japanese with word/subword tokenization + vocabulary construction algorithm informationโ129Updated last year
- A Japanese NLP Library using spaCy as framework based on Universal Dependenciesโ756Updated 7 months ago
- Sudachi in Rust ๐ฆ and new generation of SudachiPyโ319Updated this week
- aim to use JapaneseTokenizer as easy as possibleโ138Updated 5 years ago
- Japanese text normalizer for mecab-neologdโ274Updated 6 months ago
- natto-py combines the Python programming language with MeCab, the part-of-speech and morphological analyzer for the Japanese language.โ92Updated 5 months ago
- A small version of UniDic for easy pip installs.โ39Updated 4 years ago
- BERT models for Japanese text.โ514Updated 7 months ago
- Neologism dictionary based on the language resources on the Web for mecab-unidicโ83Updated 4 years ago
- A Python Module for JUMAN++/KNPโ89Updated 4 months ago
- Lightweight converter from Japanese Kana-kanji sentences into Kana-Roman.โ421Updated 2 years ago
- Japanese word embedding with Sudachi and NWJC ๐ฟโ155Updated 8 months ago
- An integrated Japanese analyzer based on foundation modelsโ130Updated last month
- ๐ฅ Vaporetto: Very accelerated pointwise prediction based tokenizerโ230Updated last week
- BERT with SentencePiece for Japanese text.โ496Updated 3 years ago
- Emotion analyzer for Japanese textโ114Updated 3 months ago
- lists of text corpus and more (mainly Japanese)โ116Updated 3 months ago
- Japanese morphological analysis engine written in pure Pythonโ859Updated last year
- A fast converter between Japanese hankaku and zenkaku charactersโ144Updated 10 months ago
- Wikipediaใ็จใใๆฅๆฌ่ชใฎๅบๆ่กจ็พๆฝๅบใใผใฟใปใใโ132Updated last year