Build software better, together

Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Translation)，etc. All codes are implemented intensorflow 2.0.

tensorflow svm word2vec crf keras similarity classification attention gensim lda fasttext ner embedding bert elmo

Updated Jul 5, 2021
Python

yongzhuo / Keras-TextClassification

Star

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

Updated Dec 19, 2020
Python

chenyuntc / PyTorchText

Star

1st Place Solution for Zhihu Machine Learning Challenge . Implementation of various text-classification models.(知乎看山杯第一名解决方案)

nlp pytorch lstm fasttext textcnn textrnn textrcnn

Updated Jul 16, 2018
Python

brightmart / bert_language_understanding

Star

Pre-training of Deep Bidirectional Transformers for Language Understanding: pre-train TextCNN

nlp text-classification question-answering document-classification transfer-learning fasttext language-model textcnn attention-is-all-you-need self-attention transformer-encoder bert-model pre-training language-understanding

Updated Jan 1, 2019
Python

ShawnyXiao / TextClassification-Keras

Star

Text classification models implemented in Keras, including: FastText, TextCNN, TextRNN, TextBiRNN, TextAttBiRNN, HAN, RCNN, RCNNVariant, etc.

nlp text-classification keras fasttext han rcnn textcnn textrnn

Updated May 21, 2021
Python

mayabot / mynlp

Star

一个生产级、高性能、模块化、可扩展的中文NLP工具包。（中文分词、平均感知机、fastText、拼音、新词发现、分词纠错、BM25、人名识别、命名实体、自定义词典）

nlp segment pinyin fasttext starspace

Updated Jul 7, 2021
Java

oborchers / Fast_Sentence_Embeddings

Star

Compute Sentence Embeddings Fast!

cython embeddings gensim fse fasttext word2vec-model maxpooling document-similarity wordembedding sif sentence-similarity sentence-embeddings sentence-representation usif gensim-model swem

Updated Apr 10, 2021
Python

AnubhavGupta3377 / Text-Classification-Models-Pytorch

Star

Implementation of State-of-the-art Text Classification Models in Pytorch

nlp deep-learning pytorch recurrent-neural-networks transformer classification seq2seq attention convolutional-neural-networks fasttext rcnn

Updated Jan 5, 2019
Python

ThoughtRiver / lmdb-embeddings

Star

Fast word vectors with little memory usage in Python

memory text word word2vec lmdb embeddings speed gensim glove vectors fasttext magnitude

Updated Jun 26, 2021
Python

ncbi-nlp / BioSentVec

Star

BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences

natural-language-processing word-embeddings pubmed fasttext mimic-iii bionlp sentence-similarity sentence-embeddings sent2vec

Updated Feb 26, 2020
Jupyter Notebook

apcode / tensorflow_fasttext

Star

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

tensorflow fasttext language-identification text-classifier

Updated Jul 18, 2018
Python

brightmart / ai_law

Star

all kinds of baseline models for long text classificaiton( text categorization)

law ai text-classification crime attention fasttext relevant-articles textcnn text-categorization hierarchical-attention-network accusation

Updated Feb 20, 2019
Python

bamtercelboo / cw2vec

Star

cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information

word2vec embeddings fasttext cw2vec stroke-information

Updated Jan 22, 2019
C++

vrasneur / pyfasttext

Star

Yet another Python binding for fastText

python nlp machine-learning numpy python-bindings fasttext word-vectors

Updated Dec 8, 2018
Python

giacbrd / ShallowLearn

Star

An experiment about re-implementing supervised learning models based on shallow neural network approaches (e.g. fastText) with some additional exclusive features and nice API. Written in Python and fully compatible with Scikit-learn.