SPINE
by harsh19
Code for SPINE - Sparse Interpretable Neural Embeddings. Jhamtani H., Pruthi D., Subramanian A.*, Berg-Kirkpatrick T., Hovy E. AAAI 2018
AI summary
Embedding transformer
Transforms existing word embeddings into more interpretable ones by applying a novel extension of k-sparse autoencoder with stricter sparsity constraints
- stars
- 52
- forks
- 11
- watching
- 7
Similar projects
Found by comparing what the projects do, not just their names.
Embeddings
Provides fast and efficient word embeddings for natural language processing.
Character embedding generator
This repository provides an unsupervised approach to learning character-aware word and context embeddings.
NLP embedders
Develops unified sentence embedding models for NLP tasks
Word embedding model
A project implementing a method to incorporate morphological information into word embeddings using a neural network model
Graph Embedder
A sparsity-aware implementation of a deep learning algorithm for graph embedding with text information.
Word Embeddings
This project generates Spanish word embeddings using fastText on large corpora.
Vector embedding utility
A fast and efficient utility package for utilizing vector embeddings in machine learning models
Language embeddings
Provides pre-trained ELMo representations for multiple languages to improve NLP tasks.
Word embedding trainer
Improves word embeddings by training with adversarial objectives
Word embeddings
Multi-sense word embeddings learned from visual cooccurrences
Word embeddings library
This implementation provides a way to represent words as multivariate Gaussian distributions, allowing scalable word embeddings.
NLP model reproducer
Reproduces the results of an ACL 2018 paper on simple word-embedding-based models for natural language processing tasks.
Embedding models
Code for training universal paraphrastic sentence embeddings and models on semantic similarity tasks
Text embedding toolkit
A utility class for generating and evaluating document representations using word embeddings.
Materials Embeddings
Unsupervised word embeddings capture latent knowledge from materials science literature
