148 Open source projects that are alternatives of or similar to Lightly

Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec from this paper https://arxiv.org/abs/1605.02019

Tensorflow implementation of "Tracking the World State with Recurrent Entity Networks" [https://arxiv.org/abs/1612.03969] by Henaff, Weston, Szlam, Bordes, and LeCun.

Text2Text: Cross-lingual natural language processing and generation toolkit

a contextual search engine for software packages built on import2vec embeddings (https://www.code-compass.com)

Compact high quality word embeddings for Russian language

Persian sentiment analysis ( آناکاوی سهش های فارسی | تحلیل احساسات فارسی )

Google News and Leo Tolstoy: Visualizing Word2Vec Word Embeddings using t-SNE.

Graph convolutional neural network for multirelational link prediction

Colab Compatible FastAI notebooks for NLP and Computer Vision Datasets

Text Classification in Turkish Texts with Bert

Sentiment analysis of tweets in Russian using Convolutional Neural Networks (CNN) with Word2Vec embeddings.

Intelligent Word Embeddings of Free-Text Radiology Reports

TensorFlow implementation of word2vec applied on https://www.kaggle.com/tamber/steam-video-games dataset, using both CBOW and Skip-gram.

Knowledge Graph Embedding LDA. AAAI 2017

Recommender Systems Paperlist that I am interested in

JavaScript embedder for Wolfram Cloud notebooks

PyTorch library for transforming entities like companies, products, etc. into vectors to support scalable Record Linkage / Entity Resolution using Approximate Nearest Neighbors.

(BOW, TF-IDF, Word2Vec, BERT) Word Embeddings + (SVM, Naive Bayes, Decision Tree, Random Forest) Base Classifiers + Pre-trained BERT on Tensorflow Hub + 1-D CNN and Bi-Directional LSTM on IMDB Movie Reviews Dataset

Natural Language Processing Pipeline - Sentence Splitting, Tokenization, Lemmatization, Part-of-speech Tagging and Dependency Parsing

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

Load embeddings and featurize your sentences.

Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".

A high-performance distributed deep learning system targeting large-scale and automated distributed training.

Information Retrieval in High Dimensional Data (class deliverables)

Tensorflow Implementation of Relation Networks for the bAbI QA Task, detailed in "A Simple Neural Network Module for Relational Reasoning," [https://arxiv.org/abs/1706.01427] by Santoro et. al.

Sentiment Analysis: Deep Bi-LSTM+attention model

Tutorials for Machine Learning on Graphs

Compass-aligned Distributional Embeddings. Align embeddings from different corpora

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

Cleora AI is a general-purpose model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data.

Reference implementations of popular DL models missing from keras-applications & keras-contrib

An implementation of the Watset clustering algorithm in Java.

Network Embedding Survey and Resources

Compute Sentence Embeddings Fast!

📖Notes and remarks on Machine Learning related papers

Face Recognition using the FaceNet model and MLKit on Android.

Neural Code Comprehension: A Learnable Representation of Code Semantics

Fuzzy string matching, grouping, and evaluation.

REST API for sentence tokenization and embedding using Multilingual Universal Sentence Encoder.

R package to Embed All the Things! using StarSpace

Data Sets and Models for Evaluation of Lexical Semantic Change Detection

Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.

🚣 A simple recommendation engine (by way of convolutions and embeddings) written in TensorFlow

A vector database for machine learning embeddings.

VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning

A library for transfer learning by reusing parts of TensorFlow models.

Deep Character CNN LSTM Encoder with Classification and Similarity Models

Implemented User Based and Item based Recommendation System along with state of the art Deep Learning Techniques

SANSA Machine Learning Layer

A python package to run contextualized topic modeling. CTMs combine BERT with topic models to get coherent topics. Also supports multilingual tasks. Cross-lingual Zero-shot model published at EACL 2021.

Neural bag of words code search implementation using PyTorch and data from the CodeSearchNet project.

CODER: Knowledge infused cross-lingual medical term embedding for term normalization. [JBI, ACL-BioNLP 2022]

Neural network transition-based dependency parser (in Rust)

Concatenate word and character embeddings in Keras

Implementation of IR2Vec, published in ACM TACO

Nimfa: Nonnegative matrix factorization in Python

Fast word vectors with little memory usage in Python

Vector Hub - Library for easy discovery, and consumption of State-of-the-art models to turn data into vectors. (text2vec, image2vec, video2vec, graph2vec, bert, inception, etc)

Read and use word2vec vectors in Go

Embedded UIScrollView for iOS.