GensimTopic Modelling for Humans
Stars: ✭ 12,763 (+91064.29%)
Elmo TutorialA short tutorial on Elmo training (Pre trained, Training on new data, Incremental training)
Stars: ✭ 145 (+935.71%)
Text SummarizerPython Framework for Extractive Text Summarization
Stars: ✭ 96 (+585.71%)
LftmImproving topic models LDA and DMM (one-topic-per-document model for short texts) with word embeddings (TACL 2015)
Stars: ✭ 168 (+1100%)
Lstm Context EmbeddingsAugmenting word embeddings with their surrounding context using bidirectional RNN
Stars: ✭ 57 (+307.14%)
ShallowlearnAn 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.
Stars: ✭ 196 (+1300%)
ScattertextBeautiful visualizations of how language differs among document types.
Stars: ✭ 1,722 (+12200%)
Concise Ipython Notebooks For Deep LearningIpython Notebooks for solving problems like classification, segmentation, generation using latest Deep learning algorithms on different publicly available text and image data-sets.
Stars: ✭ 23 (+64.29%)
Nlp NotebooksA collection of notebooks for Natural Language Processing from NLP Town
Stars: ✭ 513 (+3564.29%)
MagnitudeA fast, efficient universal vector embedding utility package.
Stars: ✭ 1,394 (+9857.14%)
DebiasweRemove problematic gender bias from word embeddings.
Stars: ✭ 175 (+1150%)
Dict2vecDict2vec is a framework to learn word embeddings using lexical dictionaries.
Stars: ✭ 91 (+550%)
Question GenerationGenerating multiple choice questions from text using Machine Learning.
Stars: ✭ 227 (+1521.43%)
Textblob ArArabic support for textblob
Stars: ✭ 60 (+328.57%)
MimickCode for Mimicking Word Embeddings using Subword RNNs (EMNLP 2017)
Stars: ✭ 152 (+985.71%)
Pytorch Sentiment AnalysisTutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+22821.43%)
WordnetembeddingsObtaining word embeddings from a WordNet ontology
Stars: ✭ 33 (+135.71%)
Fasttext.jsFastText for Node.js
Stars: ✭ 127 (+807.14%)
InltkNatural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need
Stars: ✭ 702 (+4914.29%)
GermanwordembeddingsToolkit to obtain and preprocess german corpora, train models using word2vec (gensim) and evaluate them with generated testsets
Stars: ✭ 189 (+1250%)
FlairA very simple framework for state-of-the-art Natural Language Processing (NLP)
Stars: ✭ 11,065 (+78935.71%)
Deep learning nlpKeras, PyTorch, and NumPy Implementations of Deep Learning Architectures for NLP
Stars: ✭ 407 (+2807.14%)
ChakinSimple downloader for pre-trained word vectors
Stars: ✭ 323 (+2207.14%)
Easy BertA Dead Simple BERT API for Python and Java (https://github.com/google-research/bert)
Stars: ✭ 106 (+657.14%)
TextheroText preprocessing, representation and visualization from zero to hero.
Stars: ✭ 2,407 (+17092.86%)
FastrtextR wrapper for fastText
Stars: ✭ 103 (+635.71%)
WordgcnACL 2019: Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Stars: ✭ 230 (+1542.86%)
Postgres Word2vecutils to use word embedding like word2vec vectors in a postgres database
Stars: ✭ 96 (+585.71%)
Sifrank zh基于预训练模型的中文关键词抽取方法(论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model 的中文版代码)
Stars: ✭ 175 (+1150%)
Glove As A Tensorflow Embedding LayerTaking a pretrained GloVe model, and using it as a TensorFlow embedding weight layer **inside the GPU**. Therefore, you only need to send the index of the words through the GPU data transfer bus, reducing data transfer overhead.
Stars: ✭ 85 (+507.14%)
ClustercatFast Word Clustering Software
Stars: ✭ 65 (+364.29%)
BiosentvecBioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences
Stars: ✭ 308 (+2100%)
Nlp overviewOverview of Modern Deep Learning Techniques Applied to Natural Language Processing
Stars: ✭ 1,104 (+7785.71%)
Chameleon recsysSource code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (+1342.86%)
Average Word2vec🔤 Calculate average word embeddings (word2vec) from documents for transfer learning
Stars: ✭ 52 (+271.43%)
EmbeddingsvizVisualize word embeddings of a vocabulary in TensorBoard, including the neighbors
Stars: ✭ 40 (+185.71%)
Top2vecTop2Vec learns jointly embedded topic, document and word vectors.
Stars: ✭ 972 (+6842.86%)
Syntree2vecAn algorithm to augment syntactic hierarchy into word embeddings
Stars: ✭ 9 (-35.71%)
JfasttextJava interface for fastText
Stars: ✭ 193 (+1278.57%)
Text2vecFast vectorization, topic modeling, distances and GloVe word embeddings in R.
Stars: ✭ 715 (+5007.14%)
Hash EmbeddingsPyTorch implementation of Hash Embeddings (NIPS 2017). Submission to the NIPS Implementation Challenge.
Stars: ✭ 126 (+800%)
MetaA Modern C++ Data Sciences Toolkit
Stars: ✭ 600 (+4185.71%)
Spanish Word EmbeddingsSpanish word embeddings computed with different methods and from different corpora
Stars: ✭ 236 (+1585.71%)
Bert Embedding🔡 Token level embeddings from BERT model on mxnet and gluonnlp
Stars: ✭ 424 (+2928.57%)
Dna2vecdna2vec: Consistent vector representations of variable-length k-mers
Stars: ✭ 117 (+735.71%)
WegoWord Embeddings (e.g. Word2Vec) in Go!
Stars: ✭ 336 (+2300%)
Vec4irWord Embeddings for Information Retrieval
Stars: ✭ 188 (+1242.86%)
DanlpDaNLP is a repository for Natural Language Processing resources for the Danish Language.
Stars: ✭ 111 (+692.86%)
two-stream-cnnA two-stream convolutional neural network for learning abitrary similarity functions over two sets of training data
Stars: ✭ 24 (+71.43%)
HiCECode for ACL'19 "Few-Shot Representation Learning for Out-Of-Vocabulary Words"
Stars: ✭ 56 (+300%)
KoanA word2vec negative sampling implementation with correct CBOW update.
Stars: ✭ 232 (+1557.14%)
Datastories Semeval2017 Task4Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Stars: ✭ 184 (+1214.29%)
KadotKadot, the unsupervised natural language processing library.
Stars: ✭ 108 (+671.43%)