155 Open source projects that are alternatives of or similar to simple_elmo

中文预训练模型生成字向量学习，测试BERT，ELMO的中文效果

Gaussian node embeddings. Implementation of "Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking".

Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.

📋 Survey papers summarizing advances in deep learning, NLP, CV, graphs, reinforcement learning, recommendations, graphs, etc.

Complete Code for "Hard-Aware-Deeply-Cascaded-Embedding"

Basic Utilities for PyTorch Natural Language Processing (NLP)

Code and data for the paper 'Classifying Graphs as Images with Convolutional Neural Networks' (new title: 'Graph Classification with 2D Convolutional Neural Networks')

Representing research papers as vectors / latent representations.

dna2vec: Consistent vector representations of variable-length k-mers

An implementation of word2vec applied to [stanford philosophy encyclopedia](http://plato.stanford.edu/)

Code for papers "Hashing with Mutual Information" (TPAMI 2019) and "Hashing with Binary Matrix Pursuit" (ECCV 2018)

scikit-fusion: Data fusion via collective latent factor models

CoFactor: Regularizing Matrix Factorization with Item Co-occurrence

Dict2vec is a framework to learn word embeddings using lexical dictionaries.

🍔

100+ Chinese Word Vectors 上百种预训练中文词向量

Elasticsearch plugin for nearest neighbor search. Store vectors and run similarity search using exact and approximate algorithms.

A small, interpretable codebase containing the re-implementation of a few "deep" NLP models in PyTorch. Colab notebooks to run with GPUs. Models: word2vec, CNNs, transformer, gpt.

Reasoning Over Knowledge Graph Paths for Recommendation

Visualize word embeddings of a vocabulary in TensorBoard, including the neighbors

PyTorch implementation of Hash Embeddings (NIPS 2017). Submission to the NIPS Implementation Challenge.

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

Word Embeddings for Information Retrieval

A curated list of awesome embedding models tutorials, projects and communities.

Implementation of triplet loss in TensorFlow

Data augmentation for NLP, presented at EMNLP 2019

A fast, efficient universal vector embedding utility package.

a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)

R wrapper for fastText

Making sense embedding out of word embeddings using graph-based word sense induction

Reference implementation of the paper VERSE: Versatile Graph Embeddings from Similarity Measures

entity2rec generates item recommendation using property-specific knowledge graph embeddings

WWW 2018: CESI: Canonicalizing Open Knowledge Bases using Embeddings and Side Information

Chronic Disease Prediction Using Medical Notes

An implementation of skip-thought vectors in Tensorflow

One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques

Repository for the word embeddings experiments described in "Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource", presented at LREC 2016.

Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.

Discover relevant information about categorical data with entity embeddings using Neural Networks (powered by Keras)

Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification

Context-sensitive word embeddings with subwords. In Rust.

🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

The Continuous Bag-of-Words model (CBOW) is frequently used in NLP deep learning. It's a model that tries to predict words given the context of a few words before and a few words after the target word.

Character-based word embeddings model based on RNN for handling real world texts

finalfusion embeddings in Rust

Tool for interactive embeddings visualization

Rare pupper image compression model for word-embedding-esque operations.

LASER multilingual sentence embeddings as a pip package

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

PyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook AI Research (FAIR) in ICLR 2016.

Web based semantic visualization tool

A sophisticated smart symptom search engine

🍊 🎑 Orange3 add-on for dealing with image related tasks

Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".

Solves basic Russian NLP tasks, API for lower level Natasha projects

Reference implementation of Diffusion2Vec (Complenet 2018) built on Gensim and NetworkX.

Toolkit to help understand "what lies" in word embeddings. Also benchmarking!

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

Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.

A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"