gzglss / All4NLP

All For NLP, especially Chinese.

All4NLP

Leading Track

Research

NLP Progress

Framework & Toolkit

facebookresearch/pytext: A natural language modeling framework based on PyTorch
- deeplearning NLP with PyTorch
- Text classifiers, Sequence taggers, Joint intent-slot model and Contextual intent-slot models
- C++ server example
zalandoresearch/flair: A very simple framework for state-of-the-art Natural Language Processing (NLP)
- NER, POS, sense disambiguation and classification
- on top of PyTorch
pytorch/fairseq: Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
- Seq2Seq modeling
- on top of PyTorch
BrikerMan/Kashgari: Kashgari is a Production-ready NLP Transfer learning framework for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.
- Text labeling, classification, Pre-trained
- on top of Tensorflow
asyml/texar: Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow
- NLP Toolkit
- on top of Tensorflow
stanfordnlp/stanza: Official Stanford NLP Python Library for Many Human Languages
- on top of Pytorch
- speed, prodcution system use
nltk/nltk: NLTK Source
- education and research tool
- learning and exploring NLP concepts
sloria/TextBlob: Simple, Pythonic, text processing--Sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more.
- on top of NLTK
- fast-prtotyping
- applications don't require highly performance
spaCy · Industrial-strength Natural Language Processing in Python
- fast
- streamlined
- production-ready
- chartbeat-labs/textacy: NLP, before and after spaCy

Tokenizer

Seq2Seq

Text First

Task & Model

Language Model

2020 Chinese-Bert CLUEbenchmark/CLUEPretrainedModels
2019 GPT2+Chinese Morizeyao/GPT2-Chinese: Chinese version of GPT2 training code, using BERT tokenizer.
2019 Bert-wwm ymcui/Chinese-BERT-wwm: Pre-Training with Whole Word Masking for Chinese BERT（中文 BERT-wwm 系列模型）
2019 Toolkit huggingface/pytorch-transformers: 👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)
2019 MASK google-research/bert: TensorFlow code and pre-trained models for BERT
2019 Permutation zihangdai/xlnet: XLNet: Generalized Autoregressive Pretraining for Language Understanding
2019 MultiTask PaddlePaddle/ERNIE: An Implementation of ERNIE For Language Understanding
2019 Attention kimiyoung/transformer-xl
2019 LM openai/gpt-2: Code for the paper "Language Models are Unsupervised Multitask Learners"
2018 TwoLMs ELMo: Deep contextualized word representations
2018 Co-occurrence stanfordnlp/GloVe: GloVe model for distributed word representation
2019 facebookresearch/fastText: Library for fast text representation and classification.
2019 Word2vec Embedding/Chinese-Word-Vectors: 100+ Chinese Word Vectors 上百种预训练中文词向量
2018 Word2vec Chinese-Word-Vectors
2018 LSTM 递归神经网络 | TensorFlow
2013 Google Code Archive - Long-term storage for Google Code Project Hosting.

Text Generation

2020 Toolkit RUCAIBox/TextBox: TextBox is an open-source library for building text generation system.
2020 Awesome tokenmill/awesome-nlg: A curated list of resources dedicated to Natural Language Generation (NLG)
2018 BenchMark geek-ai/Texygen: A text generation benchmarking platform
2018 RNN docs/text_generation.ipynb at master · tensorflow/docs
2019 Tookit on top of TF asyml/texar: Toolkit for Text Generation and Beyond

Classification

Collection brightmart/text_classification: all kinds of text classification models and more with deep learning

NLU & IE

QA

2020 Toolkit RUCAIBox/CRSLab: CRSLab is an open-source toolkit for building Conversational Recommender System (CRS).
2018 5hirish/adam_qas: ADAM - A Question Answering System. Inspired from IBM Watson

Similarity

2019 Sentence UKPLab/sentence-transformers: Sentence Embeddings with BERT & XLNet
2019 Sentence hanxiao/bert-as-service: Mapping a variable-length sentence to a fixed-length vector using BERT model
2018 Sentence explosion/sense2vec: 🦆 Use NLP to go beyond vanilla word2vec
2019 Sentence gensim: models.doc2vec – Doc2vec paragraph embeddings
2014 Sentence klb3713/sentence2vec: Tools for mapping a sentence with arbitrary length to vector space
2019 Doc+Sentence+Word gensim: Topic modelling for humans
2019 MinHash ekzhu/datasketch: MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++
2019 LevenshteinDistance ztane/python-Levenshtein: The Levenshtein Python C extension module contains functions for fast computation of Levenshtein distance and string similarity
2018 Graph caesar0301/graphsim: Graph similarity algorithms based on NetworkX.

Pinyin

2019 Pinyin mozillazg/python-pinyin: 汉字转拼音 (pypinyin)

Visualization

2020 Explain jalammar/ecco: Visualize and explore NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2).
2019 Word JasonKessler/scattertext: Beautiful visualizations of how language differs among document types.
2019 Bert GPT jessevig/bertviz: Tool for visualizing attention in the Transformer model (BERT and OpenAI GPT-2)
2019 MLC marcotcr/lime: Lime: Explaining the predictions of any machine learning classifier
2019 Graph Visualization Framework antvis/G6: ♾ A Graph Visualization Framework in JavaScript
2017 Neo4j D3 eisman/neo4jd3: Neo4j graph visualization using D3.js
2019 Neo4j browser neo4j-contrib/neovis.js: Neo4j + vis.js = neovis.js. Graph visualizations in the browser with data from Neo4j.
2019 Neo4j 3D jexp/neo4j-3d-force-graph: Experiments with Neo4j & 3d-force-graph https://github.com/vasturiano/3d-force-graph
2019 Interactive Graphvizz magjac/graphviz-visual-editor: A web application for interactive visual editing of Graphviz graphs described in the DOT language.
2019 graphviz Python mapio/GraphvizAnim: A tool to create animated graph visualizations, based on graphviz.

Readability

2019 Kinds of indexes shivam5992/textstat: python package to calculate readability statistics of a text object - paragraphs, sentences, articles.
2019 in Spacy mholtzscher/spacy_readability: spaCy pipeline component for adding text readability meta data to Doc objects.

Translation

2019 XLM facebookresearch/XLM: PyTorch original implementation of Cross-lingual Language Model Pretraining.
2018 Microsoft Based on Phrase Microsoft/NPMT: Towards Neural Phrase-based Machine Translation
2019 Google Based on Seq2Seq and Attention tensorflow/nmt: TensorFlow Neural Machine Translation Tutorial
2019 Google Based on Pure Attention models/official/transformer at master · tensorflow/models
2019 Facebook Based on CNN pytorch/fairseq: Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
2019 Facebook Based on Unsupervised facebookresearch/UnsupervisedMT: Phrase-Based & Neural Unsupervised Machine Translation
2019 DeepL Basedon CNN (Not Open Source) DeepL Translator DeepL 基于 CNN 的翻译工具
2019 OpenNMT OpenNMT/OpenNMT: Open Source Neural Machine Translation

Style Transfer

2020 Awesome fuzhenxin/Style-Transfer-in-Text: Paper List for Style Transfer in Text

Tricks

2020 让PyTorch训练速度更快，你需要掌握这17种方法
2017 Deep Learning for NLP Best Practices

Dataset

Learn Here

Experts

About

All For NLP, especially Chinese.

MIT License

Languages

Language:Jupyter Notebook 99.4%Language:Python 0.6%Language:Cython 0.0%