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

0 0 1 Python

COMMITS

/ hanlp/version.py
dev
October 19, 2025
H
TF is deprecated in Transformers and no longer maintained: https://github.com/hankcs/HanLP/issues/1959
hankcs committed
942ce93
September 7, 2025
H
Fix stdio redirection, fix: https://github.com/hankcs/HanLP/issues/1958
hankcs committed
5f46aec
January 13, 2025
H
Release Ancient Chinese models for tokenization, lemmatization, part-of-speech tagging and dependency parsing
hankcs committed
2eb94f2
December 29, 2024
H
Release `2.1.0`
hankcs committed
749ecf6
December 7, 2024
H
Fix `dep` key of `to_pretty`
hankcs committed
c01f4f6
December 2, 2024
H
Fix loading issue of fine-tuned NER models
hankcs committed
1197741
October 8, 2024
H
Avoid redundant downloading and decompressing across processes
hankcs committed
32428a2
September 8, 2024
H
Fix extrapolation in relative transformer, fix: https://github.com/hankcs/HanLP/issues/1906
hankcs committed
4280529
August 22, 2024
H
Support new versions of tensorflow and numpy
hankcs committed
e64efb8
August 18, 2024
H
Parse raw sentences for custom tags, fix: https://github.com/hankcs/HanLP/issues/1903
hankcs committed
022d0fb
July 11, 2024
H
Support Python 3.6 on Windows
hankcs committed
77fe054
March 23, 2024
H
Fix phrasetree fix: https://github.com/hankcs/HanLP/issues/1886
hankcs committed
dfd8d5e
February 24, 2024
H
Fix tokenization of Korean chars fix: https://github.com/hankcs/HanLP/issues/1877
hankcs committed
785bed5
December 22, 2023
H
Mirror tokenizers from our file servers fix: https://github.com/hankcs/HanLP/issues/1865
hankcs committed
beab770
November 28, 2023
H
Pin the version of `tokenizers` on macOS Python3.6 to compile it
hankcs committed
0450298
H
Update resource & mirror sites
hanlpbot committed
6bbf1ff
October 19, 2023
H
Resize vocab and classifier automatically for taggers
hanlpbot committed
19eb67a
October 14, 2023
H
Unpin the version of `tokenizers` fix: https://github.com/hankcs/HanLP/issues/1849
hanlpbot committed
4c1f457
May 23, 2023
H
Support TensorFlow on Python 3.10 fix: https://github.com/hankcs/HanLP/issues/1821
hankcs committed
81795fc
April 14, 2023
H
Support overriding `batch_size` for a constituency parser fix: https://github.com/hankcs/HanLP/issues/1815
hankcs committed
5997c59
April 8, 2023
H
Use the original tokens to build constituency tree fix: https://github.com/hankcs/HanLP/issues/1811
hankcs committed
135a399
March 25, 2023
H
Lazily load TensorFlow fix: https://github.com/hankcs/HanLP/issues/1810
hankcs committed
ea9565e
March 10, 2023
H
Add `protobuf<3.19` to tf dependencies fix: https://github.com/hankcs/HanLP/issues/1809
hankcs committed
af70075
December 7, 2022
H
Implementation of "Graph Pre-training for AMR Parsing and Generation"
hankcs committed
a8ac5e1
November 4, 2022
H
Add dependency on sentencepiece
hankcs committed
266a783
November 3, 2022
H
Improve how MTL handles empty strings
hankcs committed
025f964
September 28, 2022
H
Release language identification APIs which can recognize 176 languages
hankcs committed
5ba95ea
August 27, 2022
H
Make empty string consistent between STL and MTL: https://github.com/hankcs/HanLP/issues/1778
hankcs committed
0133188
August 26, 2022
H
Fix empty string tokens in `TransformerSequenceTokenizer` fix: https://github.com/hankcs/HanLP/issues/1778
hankcs committed
9210d5a
August 11, 2022
H
Fix tokenizer evaluation during training fix: https://github.com/hankcs/HanLP/issues/1773
hankcs committed
ea17ae2
July 31, 2022
H
Update MUL-MTL model with SDP fixed
hankcs committed
8fe00ad
July 18, 2022
H
avoid cycle between a pair of nodes
hankcs committed
4339b09
July 7, 2022
H
Fix decompression on Windows fix: https://github.com/hankcs/HanLP/issues/1757
hankcs committed
2a628ea
July 6, 2022
H
Fix cases that a single char gets split into multiple subtokens fix: https://github.com/hankcs/HanLP/issues/1756 fix: https://github.com/hankcs/HanLP/issues/1754
hankcs committed
5d14517
June 19, 2022
H
Replace `XLM_SMALL` with `MMINILMV2L6`
hankcs committed
3d01174
June 16, 2022
H
Update two tok models trained on 100m corpora
hankcs committed
7616dbb
June 15, 2022
H
Release a multilingual tokenizer trained with MiniLMv2
hankcs committed
584ce7e
June 12, 2022
H
Update two tok models with F1 > 98%
hankcs committed
ee3d178
June 10, 2022
H
`max_sequence_length` of `TransformerEncoder` defaults to `max_position_embeddings`
hankcs committed
e1c0700
June 8, 2022
H
Support 130 languages trained on Universal Dependencies 2.10
hankcs committed
646ca7d
June 7, 2022
H
Support accelerated PyTorch on macOS M1 chips: https://www.hankcs.com/nlp/hanlp-official-m1-support.html
hankcs committed
924c768
April 20, 2022
H
Fix `output_spans` with `dict_combine` fix: https://github.com/hankcs/HanLP/issues/1727
hankcs committed
77217d5
April 18, 2022
H
Fix fasttext URL in `PTB_POS_RNN_FASTTEXT_EN`
hankcs committed
5317922
April 16, 2022
H
Fix matching issue caused by `dict_force` in https://github.com/hankcs/HanLP/commit/e7eb64b05b664f011cd452816ddade176dcfbb9b fix: https://github.com/hankcs/HanLP/issues/1722
hankcs committed
e52dc9f
April 15, 2022
H
Release a Chinese MRP model with Mengzi PLM
hankcs committed
9b3a786
April 14, 2022
H
Fix edge cases of empty inputs for MTL
hankcs committed
15bb02f
H
Use the latest perin-parser
hankcs committed
ea11f96
April 13, 2022
H
Release a SOTA joint Chinese-English AMR model
hankcs committed
26ff093
April 12, 2022
H
Fix training CRF in `TaggingNamedEntityRecognition`: https://bbs.hankcs.com/t/topic/4132/3?u=hankcs
hankcs committed
a808b0f
March 22, 2022
H
Optimize merging sub-tokens
hankcs committed
4467a3c