8 projects
ja-ginza-electra
Japanese multi-task CNN trained on UD-Japanese BCCWJ r2.8 + GSK2014-A(2019) + transformers-ud-japanese-electra--base. Components: transformer, parser, atteribute_ruler, ner, morphologizer, compound_splitter, bunsetu_recognizer.
ja-ginza
Japanese multi-task CNN trained on UD-Japanese BCCWJ r2.8 + GSK2014-A(2019). Assigns word2vec token vectors. Components: tok2vec, parser, ner, morphologizer, atteribute_ruler, compound_splitter, bunsetu_recognizer.
ginza
GiNZA, An Open Source Japanese NLP Library, based on Universal Dependencies
vecscan
vecscan: A Linear-scan-based High-speed Dense Vector Search Engine
bunkai
Sentence boundary disambiguation tool for Japanese texts
ginza-transformers
ginza-transformers
desuwa
Feature annotator based on KNP rule files
ja-ginza-dict
SudachiDict for ja_ginza (SudachiDict is originally developed by Works Applications Tokushima Laboratory of AI and NLP)
