Morph MORPH
SIGN IN SIGN UP
hankcs / HanLP UNCLAIMED

Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

36234 0 0 Python

COMMITS

master
October 19, 2025
H
TF is deprecated in Transformers and no longer maintained: https://github.com/hankcs/HanLP/issues/1959
hankcs committed
942ce93
September 11, 2025
H
Test on ubuntu-latest, macos-latest, windows-latest
hankcs committed
e72db55
September 7, 2025
H
Fix stdio redirection, fix: https://github.com/hankcs/HanLP/issues/1958
hankcs committed
5f46aec
January 15, 2025
H
Support reusing existing model and config for finetuning, fix: https://github.com/hankcs/HanLP/issues/1942
hankcs committed
199f3f3
January 14, 2025
H
Test on ubuntu-20.04, macos-latest, windows-latest
hankcs committed
81983df
H
Keep the new hyperparameters when fine-tuning a model, fix: https://github.com/hankcs/HanLP/issues/1942
hankcs committed
80506cf
January 13, 2025
H
Revise document
hankcs committed
a639dbc
H
Release Ancient Chinese models for tokenization, lemmatization, part-of-speech tagging and dependency parsing
hankcs committed
2eb94f2
H
Revise documents for Ancient Chinese models
hankcs committed
0636dc6
H
Release Ancient Chinese MTL model `KYOTO_EVAHAN_TOK_LEM_POS_UDEP_LZH`
hankcs committed
f717be1
January 12, 2025
H
Display the main pos by default
hankcs committed
c1aa002
H
Support XPOS for CoNLL-U
hankcs committed
7aeb0fc
H
Implement TransformerTaggingLemmatizer
hankcs committed
9988be6
H
Release Ancient Chinese tokenization model `KYOTO_EVAHAN_TOK_LZH`
hankcs committed
e8bad3f
January 11, 2025
H
Skip hidden states averaging for tokenization only models
hankcs committed
c0d5d92
H
Mirror `bert-ancient-chinese`
hankcs committed
9529587
H
Automatically detect file type by `.conllu` extension
hankcs committed
5c6d17b
January 7, 2025
H
Release `EN_TOK_LEM_POS_NER_SRL_UDEP_SDP_CON_MODERNBERT_LARGE`
hankcs committed
3185188
H
Replace `FloatTensor` with `sparse_coo_tensor`
hankcs committed
7a4b735
December 29, 2024
H
Release `2.1.0`
hankcs committed
749ecf6
H
Improve logging
hankcs committed
d4660c3
December 22, 2024
H
TransformList supports config
hankcs committed
3202623
December 28, 2024
H
Release an English MTL model with ModernBERT encoder
hankcs committed
3aba649
December 25, 2024
H
Revise documentation
hankcs committed
5698f32
December 24, 2024
H
Update eos model config to support new lines
hankcs committed
75edc60
December 23, 2024
H
Support coarse tokenization of Japanese
hankcs committed
007f29f
December 21, 2024
H
Implement `PrependSpace`
hankcs committed
c583768
H
Replace `FloatTensor` with `sparse_coo_tensor`
hankcs committed
77481bd
H
Heuristic to fix lemma for digits
hankcs committed
36c9e6f
H
Support ModernBERT as a tokenizer
hankcs committed
336fd93