Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
Support
Quality
Security
License
Reuse
GPT-powered chat for documentation, chat with your documents
Support
Quality
Security
License
Reuse
An open source library for deep learning end-to-end dialog systems and chatbots.
Support
Quality
Security
License
Reuse
An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more
Support
Quality
Security
License
Reuse
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Support
Quality
Security
License
Reuse
Google AI 2018 BERT pytorch implementation
Support
Quality
Security
License
Reuse
Extract Keywords from sentence or Replace keywords in sentences.
Support
Quality
Security
License
Reuse
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
Support
Quality
Security
License
Reuse
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识,包括面试题,各种基础知识,工程能力等等,提升核心竞争力
Support
Quality
Security
License
Reuse
Lightweight Ruby
Support
Quality
Security
License
Reuse
Python PDF Parser (Not actively maintained). Check out pdfminer.six.
Support
Quality
Security
License
Reuse
C
ChineseNlpCorpusby SophonPlus
Jupyter Notebook 
4920
Version:Current
License: No License (No License)
搜集、整理、发布 中文 自然语言处理 语料/数据集,与 有志之士 共同 促进 中文 自然语言处理 的 发展。
Support
Quality
Security
License
Reuse
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Support
Quality
Security
License
Reuse
:herb: 中文近义词:聊天机器人,智能问答工具包
Support
Quality
Security
License
Reuse
b
bob-plugin-openai-translatorby yetone
JavaScript 
4693
Version:Current
License: No License (No License)
基于 ChatGPT API 的文本翻译、文本润色、语法纠错 Bob 插件,让我们一起迎接不需要巴别塔的新时代!
Support
Quality
Security
License
Reuse
C
Chinese-Text-Classification-Pytorchby 649453932
Python 
4459
Version:Current
License: Permissive (MIT)
中文文本分类,TextCNN,TextRNN,FastText,TextRCNN,BiLSTM_Attention,DPCNN,Transformer,基于pytorch,开箱即用。
Support
Quality
Security
License
Reuse
Language Technology Platform
Support
Quality
Security
License
Reuse
vanilla javascript input mask
Support
Quality
Security
License
Reuse
Reading Wikipedia to Answer Open-Domain Questions
Support
Quality
Security
License
Reuse
汉字转拼音(pypinyin)
Support
Quality
Security
License
Reuse
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Support
Quality
Security
License
Reuse
pycorrector is a toolkit for text error correction. 文本纠错,Kenlm,ConvSeq2Seq,BERT,MacBERT,ELECTRA,ERNIE,Transformer,T5等模型实现,开箱即用。
Support
Quality
Security
License
Reuse
An Open-Source Package for Neural Relation Extraction (NRE)
Support
Quality
Security
License
Reuse
A personal experimental C++ Syntax 2 -> Syntax 1 compiler
Support
Quality
Security
License
Reuse
VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.
Support
Quality
Security
License
Reuse
Natural language detection
Support
Quality
Security
License
Reuse
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
Support
Quality
Security
License
Reuse
This project is intended to protest against the police in Japan
Support
Quality
Security
License
Reuse
Snips Python library to extract meaning from text
Support
Quality
Security
License
Reuse
Facilitating the design, comparison and sharing of deep text matching models.
Support
Quality
Security
License
Reuse
A C library for parsing/normalizing street addresses around the world. Powered by statistical NLP and open geo data.
Support
Quality
Security
License
Reuse
Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Support
Quality
Security
License
Reuse
A toy programming language written in Typescript
Support
Quality
Security
License
Reuse
extract text from any document. no muss. no fuss.
Support
Quality
Security
License
Reuse
A
Agriculture_KnowledgeGraphby qq547276542
Python 
3494
Version:Current
License: Strong Copyleft (GPL-3.0)
农业知识图谱(AgriKG):农业领域的信息检索,命名实体识别,关系抽取,智能问答,辅助决策
Support
Quality
Security
License
Reuse
百度NLP:分词,词性标注,命名实体识别,词重要性
Support
Quality
Security
License
Reuse
Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️♂️
Support
Quality
Security
License
Reuse
Collection of advice on optimizing compile times of Swift projects.
Support
Quality
Security
License
Reuse
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Support
Quality
Security
License
Reuse
A Code-First Introduction to NLP course
Support
Quality
Security
License
Reuse
Language-Agnostic SEntence Representations
Support
Quality
Security
License
Reuse
State of the Art Natural Language Processing
Support
Quality
Security
License
Reuse
A natural language date parser in Javascript
Support
Quality
Security
License
Reuse
BGP implemented in the Go Programming Language
Support
Quality
Security
License
Reuse
搜索所有中文NLP数据集,附常用英文NLP数据集
Support
Quality
Security
License
Reuse
Module for automatic summarization of text documents and HTML pages.
Support
Quality
Security
License
Reuse
:pencil2: LeetCode solutions in C++ 11 and Python3
Support
Quality
Security
License
Reuse
A simple, extensible Markov chain generator.
Support
Quality
Security
License
Reuse
A LLM based research assistant that allows you to have a conversation with a research paper
Support
Quality
Security
License
Reuse
Chronic is a pure Ruby natural language date parser.
Support
Quality
Security
License
Reuse
E
ERNIEby PaddlePaddle
Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
Python
5869
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
D
DocsGPTby arc53
GPT-powered chat for documentation, chat with your documents
Python
5774
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
D
DeepPavlovby deepmipt
An open source library for deep learning end-to-end dialog systems and chatbots.
Python
5674
Updated: 3 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
n
nlp.jsby axa-group
An NLP library for building bots, with entity extraction, sentiment analysis, automatic language identify, and so more
JavaScript
5642
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
g
gpt-neoxby EleutherAI
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Python
5633
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
B
BERT-pytorchby codertimo
Google AI 2018 BERT pytorch implementation
Python
5545
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
f
flashtextby vi3k6i5
Extract Keywords from sentence or Replace keywords in sentences.
Python
5396
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
b
bertvizby jessevig
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
Python
5282
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
N
NLP_abilityby DA-southampton
总结梳理自然语言处理工程师(NLP)需要积累的各方面知识,包括面试题,各种基础知识,工程能力等等,提升核心竞争力
Python
5206
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
m
Support
Quality
Security
License
Reuse
p
pdfminerby euske
Python PDF Parser (Not actively maintained). Check out pdfminer.six.
Python
5024
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
C
ChineseNlpCorpusby SophonPlus
搜集、整理、发布 中文 自然语言处理 语料/数据集,与 有志之士 共同 促进 中文 自然语言处理 的 发展。
Jupyter Notebook
4920
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
L
LoRAby microsoft
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Python
4881
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
S
Support
Quality
Security
License
Reuse
b
bob-plugin-openai-translatorby yetone
基于 ChatGPT API 的文本翻译、文本润色、语法纠错 Bob 插件,让我们一起迎接不需要巴别塔的新时代!
JavaScript
4693
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
C
Chinese-Text-Classification-Pytorchby 649453932
中文文本分类,TextCNN,TextRNN,FastText,TextRCNN,BiLSTM_Attention,DPCNN,Transformer,基于pytorch,开箱即用。
Python
4459
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
l
ltpby HIT-SCIR
Language Technology Platform
Python
4413
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
i
imaskjsby uNmAnNeR
vanilla javascript input mask
TypeScript
4386
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
D
DrQAby facebookresearch
Reading Wikipedia to Answer Open-Domain Questions
Python
4378
Updated: 2 y ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
p
Support
Quality
Security
License
Reuse
B
BERT-BiLSTM-CRF-NERby macanv
Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services
Python
4253
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
p
pycorrectorby shibing624
pycorrector is a toolkit for text error correction. 文本纠错,Kenlm,ConvSeq2Seq,BERT,MacBERT,ELECTRA,ERNIE,Transformer,T5等模型实现,开箱即用。
Python
4230
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
O
OpenNREby thunlp
An Open-Source Package for Neural Relation Extraction (NRE)
Python
3999
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
c
cppfrontby hsutter
A personal experimental C++ Syntax 2 -> Syntax 1 compiler
C++
3978
Updated: 2 y ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
v
vaderSentimentby cjhutto
VADER Sentiment Analysis. VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media, and works well on texts from other domains.
Python
3977
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
f
Support
Quality
Security
License
Reuse
a
albert_zhby brightmart
A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型
Python
3823
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
l
lets-get-arrestedby hamukazu
This project is intended to protest against the police in Japan
HTML
3780
Updated: 4 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
s
snips-nluby snipsco
Snips Python library to extract meaning from text
Python
3777
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
M
MatchZooby NTMC-Community
Facilitating the design, comparison and sharing of deep text matching models.
Python
3773
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
l
libpostalby openvenues
A C library for parsing/normalizing street addresses around the world. Powered by statistical NLP and open geo data.
C
3716
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
s
simpletransformersby ThilinaRajapakse
Transformers for Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Python
3698
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
b
bhai-langby DulLabs
A toy programming language written in Typescript
TypeScript
3589
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
t
textractby deanmalmgren
extract text from any document. no muss. no fuss.
HTML
3518
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
A
Agriculture_KnowledgeGraphby qq547276542
农业知识图谱(AgriKG):农业领域的信息检索,命名实体识别,关系抽取,智能问答,辅助决策
Python
3494
Updated: 2 y ago
License: Strong Copyleft (GPL-3.0)
Support
Quality
Security
License
Reuse
l
Support
Quality
Security
License
Reuse
G
GraphGPTby varunshenoy
Extrapolating knowledge graphs from unstructured text using GPT-3 🕵️♂️
JavaScript
3475
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
O
Optimizing-Swift-Build-Timesby fastred
Collection of advice on optimizing compile times of Swift projects.
Swift
3454
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
C
CLUEby CLUEbenchmark
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Python
3373
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
c
course-nlpby fastai
A Code-First Introduction to NLP course
Jupyter Notebook
3316
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
L
LASERby facebookresearch
Language-Agnostic SEntence Representations
Python
3287
Updated: 2 y ago
License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
s
spark-nlpby JohnSnowLabs
State of the Art Natural Language Processing
Scala
3279
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
c
chronoby wanasit
A natural language date parser in Javascript
TypeScript
3247
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
g
gobgpby osrg
BGP implemented in the Go Programming Language
Go
3228
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
C
CLUEDatasetSearchby CLUEbenchmark
搜索所有中文NLP数据集,附常用英文NLP数据集
Python
3211
Updated: 2 y ago
License: No License (No License)
Support
Quality
Security
License
Reuse
s
sumyby miso-belica
Module for automatic summarization of text documents and HTML pages.
Python
3172
Updated: 2 y ago
License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
L
LeetCodeby pezy
:pencil2: LeetCode solutions in C++ 11 and Python3
C++
3144
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
m
markovifyby jsvine
A simple, extensible Markov chain generator.
Python
3131
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
r
researchgptby mukulpatnaik
A LLM based research assistant that allows you to have a conversation with a research paper
Python
3108
Updated: 2 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse
c
chronicby mojombo
Chronic is a pure Ruby natural language date parser.
Ruby
3104
Updated: 4 y ago
License: Permissive (MIT)
Support
Quality
Security
License
Reuse