Natural Language Processing
metasequoiaime/chinese-ime-lm🔥 active
▲ +2 ★ this week
面向中文输入法的语言模型：语料、n-gram 统计、字级神经模型，以及判断它们好坏的评测集
🤖 Language Models
PythonGPL-3.0updated Nov 11, 2026
🏆 #5,717 overall#2077 of 2,559 in Natural Language Processing
IgarashiAkatuki /CNMBERT
基于BERT的拼音缩写/汉字谐音翻译模型，在命名实体识别，情感分析等多种任务上有应用潜力。中文拼写纠错 Chinese Spelling Correction (CSC)，互联网黑话，拼音缩写，汉字谐音
$ git clone https://github.com/IgarashiAkatuki/CNMBERT.gitStars
138
138
This week
—
Forks
5
5
Language
Python
License
AGPL-3.0
Created
Sep 14, 2024
2.2 years old
Last push
Jan 10, 2026
Categories
More in Natural Language Processing
Natural Language Processing
brightmart/nlp_chinese_corpus
▲ +2 ★ this week
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
🗂️ Text Classification❓ Question Answering🧬 Embeddings🤖 Language Models
OtherMITupdated Feb 6, 2026
Natural Language Processing
Morizeyao/GPT2-Chinese
▲ +2 ★ this week
Chinese version of GPT2 training code, using BERT tokenizer.
🤖 Language Models
PythonMITupdated Apr 25, 2024
Natural Language Processing
NLPchina/ansj_seg
▲ +1 ★ this week
ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典
JavaApache-2.0updated Nov 19, 2023
Natural Language Processing
houbb/sensitive-word
▲ +7 ★ this week
👮♂️The sensitive word tool for java.(敏感词/违禁词/违法词/脏词。基于 DFA 算法实现的高性能 java 敏感词过滤工具框架。内置支持单词标签分类分级。请勿发布涉及政治、广告、营销、翻墙、违反国家法律法规等内容。高性能敏感词检测过滤组件，附带繁体简体互换，支持全角半角互换，汉字转拼音，模糊搜索等功能。)
JavaApache-2.0updated Mar 23, 2026
Natural Language Processing
OFA-Sys/Chinese-CLIP
▲ +11 ★ this week
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Jupyter NotebookMITupdated Mar 31, 2026
Data from GitHub · snapshot Nov 13, 2026