KunWangR's starred repositories

assistant

A chat bot powered by GPT to answer questions related to documentation

Language:PythonLicense:GPL-3.0Stargazers:30Issues:0Issues:0

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

License:CC0-1.0Stargazers:15757Issues:0Issues:0

Named_Entity_Recognition_Korean_with_BERT

Implementation of NER for Korean with BERT

Language:PythonStargazers:6Issues:0Issues:0

GlobalPointer_torch

CMeEE/CBLUE/NER实体识别

Language:PythonStargazers:117Issues:0Issues:0

pycorrector

pycorrector is a toolkit for text error correction. 文本纠错,实现了Kenlm,T5,MacBERT,ChatGLM3,LLaMA等模型应用在纠错场景,开箱即用。

Language:PythonLicense:Apache-2.0Stargazers:5310Issues:0Issues:0
Language:PythonLicense:MITStargazers:1331Issues:0Issues:0

mlm_bert_traning

基于mlm方式的带有纠错功能的拼音转汉字bert预训练模型,pinyin correcter,基于pytorch框架实现

Language:PythonStargazers:41Issues:0Issues:0
License:Apache-2.0Stargazers:253Issues:0Issues:0

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonLicense:MITStargazers:19043Issues:0Issues:0

DCN

Dynamic Connected Networks for Chinese Spelling Check

Language:PythonLicense:Apache-2.0Stargazers:48Issues:0Issues:0

MuCGEC

MuCGEC中文纠错数据集及文本纠错SOTA模型开源;Code & Data for our NAACL 2022 Paper "MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction"

Language:PythonLicense:Apache-2.0Stargazers:466Issues:0Issues:0

MiduCTC-competition

文本智能校对大赛(Chinese Text Correction)的baseline

Language:PythonStargazers:61Issues:0Issues:0

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Language:PythonLicense:Apache-2.0Stargazers:35423Issues:0Issues:0

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

Language:PythonLicense:Apache-2.0Stargazers:29070Issues:0Issues:0

spacy-lookup

Named Entity Recognition based on dictionaries

Language:PythonLicense:MITStargazers:240Issues:0Issues:0

PLOME

Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021

Language:PythonLicense:Apache-2.0Stargazers:227Issues:0Issues:0

Time-NLPY

Time-NLP的Python3版本 中文时间表达识别

Language:PythonStargazers:82Issues:0Issues:0

Time_NLP

Time-NLP的python3版本 中文时间表达词转换

Language:PythonStargazers:497Issues:0Issues:0

nlpcda

一键中文数据增强包 ; NLP数据增强、bert数据增强、EDA:pip install nlpcda

Language:PythonLicense:Apache-2.0Stargazers:1712Issues:0Issues:0

iamQA

中文wiki百科QA阅读理解问答系统,使用了CCKS2016数据的NER模型和CMRC2018的阅读理解模型,还有W2V词向量搜索,使用torchserve部署

Language:PythonStargazers:89Issues:0Issues:0

ChineseMRC-Data

收集了目前为止中文领域的MRC抽取式数据集

Stargazers:113Issues:0Issues:0

QA-Survey-CN

北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答(KBQA),基于文本的问答系统(TextQA),基于表格的问答系统(TableQA)、基于视觉的问答系统(VisualQA)和机器阅读理解(MRC)等,每类任务分别对学术界和工业界进行了相关总结。

Stargazers:1648Issues:0Issues:0

Chinese-RC-Datasets

Collections of Chinese reading comprehension datasets

License:CC-BY-SA-4.0Stargazers:212Issues:0Issues:0

PaddleNLP

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.

Language:PythonLicense:Apache-2.0Stargazers:11682Issues:0Issues:0

ASRT_SpeechRecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

Language:PythonLicense:GPL-3.0Stargazers:7614Issues:0Issues:0

phkit

phoneme toolkit. 好用的音素处理工具箱,包含中文音素、英文音素、文本转拼音、文本正则化等模块。

Language:PythonLicense:MITStargazers:73Issues:0Issues:0

phonemizer

Simple text to phones converter for multiple languages

Language:PythonLicense:GPL-3.0Stargazers:1134Issues:0Issues:0

DaCiDian

DaCiDian is an open-sourced chinese mandarin lexicon for automatic speech recognition(ASR)

Language:PythonStargazers:297Issues:0Issues:0
Stargazers:33Issues:0Issues:0

FewCLUE

FewCLUE 小样本学习测评基准,中文版

Language:PythonStargazers:484Issues:0Issues:0