MimickCode for Mimicking Word Embeddings using Subword RNNs (EMNLP 2017)
Stars: ✭ 152 (+68.89%)
FlairA very simple framework for state-of-the-art Natural Language Processing (NLP)
Stars: ✭ 11,065 (+12194.44%)
Pytorch Sentiment AnalysisTutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+3465.56%)
DebiasweRemove problematic gender bias from word embeddings.
Stars: ✭ 175 (+94.44%)
Dict2vecDict2vec is a framework to learn word embeddings using lexical dictionaries.
Stars: ✭ 91 (+1.11%)
proxy-synthesisOfficial PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Stars: ✭ 30 (-66.67%)
MagnitudeA fast, efficient universal vector embedding utility package.
Stars: ✭ 1,394 (+1448.89%)
Question GenerationGenerating multiple choice questions from text using Machine Learning.
Stars: ✭ 227 (+152.22%)
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 (+104.44%)
Textblob ArArabic support for textblob
Stars: ✭ 60 (-33.33%)
SPL-ADVisEPyTorch code for BMVC 2018 paper: "Self-Paced Learning with Adaptive Visual Embeddings"
Stars: ✭ 20 (-77.78%)
LftmImproving topic models LDA and DMM (one-topic-per-document model for short texts) with word embeddings (TACL 2015)
Stars: ✭ 168 (+86.67%)
simple-cnapsSource codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)
Stars: ✭ 88 (-2.22%)
Elmo TutorialA short tutorial on Elmo training (Pre trained, Training on new data, Incremental training)
Stars: ✭ 145 (+61.11%)
HiCECode for ACL'19 "Few-Shot Representation Learning for Out-Of-Vocabulary Words"
Stars: ✭ 56 (-37.78%)
ScattertextBeautiful visualizations of how language differs among document types.
Stars: ✭ 1,722 (+1813.33%)
GPQGeneralized Product Quantization Network For Semi-supervised Image Retrieval - CVPR 2020
Stars: ✭ 60 (-33.33%)
KadotKadot, the unsupervised natural language processing library.
Stars: ✭ 108 (+20%)
KoanA word2vec negative sampling implementation with correct CBOW update.
Stars: ✭ 232 (+157.78%)
Text SummarizerPython Framework for Extractive Text Summarization
Stars: ✭ 96 (+6.67%)
MinkLocMultimodalMinkLoc++: Lidar and Monocular Image Fusion for Place Recognition
Stars: ✭ 65 (-27.78%)
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 (+117.78%)
Vec4irWord Embeddings for Information Retrieval
Stars: ✭ 188 (+108.89%)
Nlp overviewOverview of Modern Deep Learning Techniques Applied to Natural Language Processing
Stars: ✭ 1,104 (+1126.67%)
TextheroText preprocessing, representation and visualization from zero to hero.
Stars: ✭ 2,407 (+2574.44%)
visual-compatibilityContext-Aware Visual Compatibility Prediction (https://arxiv.org/abs/1902.03646)
Stars: ✭ 92 (+2.22%)
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 (+94.44%)
Npair loss pytorchImproved Deep Metric Learning with Multi-class N-pair Loss Objective
Stars: ✭ 75 (-16.67%)
GensimTopic Modelling for Humans
Stars: ✭ 12,763 (+14081.11%)
triplet-loss-pytorchHighly efficient PyTorch version of the Semi-hard Triplet loss ⚡️
Stars: ✭ 79 (-12.22%)
wefeWEFE: The Word Embeddings Fairness Evaluation Framework. WEFE is a framework that standardizes the bias measurement and mitigation in Word Embeddings models. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!
Stars: ✭ 164 (+82.22%)
Hash EmbeddingsPyTorch implementation of Hash Embeddings (NIPS 2017). Submission to the NIPS Implementation Challenge.
Stars: ✭ 126 (+40%)
Dna2vecdna2vec: Consistent vector representations of variable-length k-mers
Stars: ✭ 117 (+30%)
CVPR2020 PADS(CVPR 2020) This repo contains code for "PADS: Policy-Adapted Sampling for Visual Similarity Learning", which proposes learnable triplet mining with Reinforcement Learning.
Stars: ✭ 57 (-36.67%)
DanlpDaNLP is a repository for Natural Language Processing resources for the Danish Language.
Stars: ✭ 111 (+23.33%)
Spanish Word EmbeddingsSpanish word embeddings computed with different methods and from different corpora
Stars: ✭ 236 (+162.22%)
Easy BertA Dead Simple BERT API for Python and Java (https://github.com/google-research/bert)
Stars: ✭ 106 (+17.78%)
sisterSImple SenTence EmbeddeR
Stars: ✭ 66 (-26.67%)
FastrtextR wrapper for fastText
Stars: ✭ 103 (+14.44%)
WordgcnACL 2019: Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Stars: ✭ 230 (+155.56%)
Postgres Word2vecutils to use word embedding like word2vec vectors in a postgres database
Stars: ✭ 96 (+6.67%)
acl2017 document clusteringcode for "Determining Gains Acquired from Word Embedding Quantitatively Using Discrete Distribution Clustering" ACL 2017
Stars: ✭ 21 (-76.67%)
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 (-5.56%)
Chameleon recsysSource code of CHAMELEON - A Deep Learning Meta-Architecture for News Recommender Systems
Stars: ✭ 202 (+124.44%)
ClustercatFast Word Clustering Software
Stars: ✭ 65 (-27.78%)
Word2VecfJavaWord2VecfJava: Java implementation of Dependency-Based Word Embeddings and extensions
Stars: ✭ 14 (-84.44%)
JfasttextJava interface for fastText
Stars: ✭ 193 (+114.44%)
tf retrieval baselineA Tensorflow retrieval (space embedding) baseline. Metric learning baseline on CUB and Stanford Online Products.
Stars: ✭ 39 (-56.67%)
PersianNERNamed-Entity Recognition in Persian Language
Stars: ✭ 48 (-46.67%)
fuzzymaxCode for the paper: Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors, ICLR 2019.
Stars: ✭ 43 (-52.22%)
two-stream-cnnA two-stream convolutional neural network for learning abitrary similarity functions over two sets of training data
Stars: ✭ 24 (-73.33%)
GermanwordembeddingsToolkit to obtain and preprocess german corpora, train models using word2vec (gensim) and evaluate them with generated testsets
Stars: ✭ 189 (+110%)