All Projects → fursovia → geometric_embedding

fursovia / geometric_embedding

Licence: other
"Zero-Training Sentence Embedding via Orthogonal Basis" paper implementation

Programming Languages

python
139335 projects - #7 most used programming language
perl
6916 projects

Projects that are alternatives of or similar to geometric embedding

Cx db8
a contextual, biasable, word-or-sentence-or-paragraph extractive summarizer powered by the latest in text embeddings (Bert, Universal Sentence Encoder, Flair)
Stars: ✭ 164 (+763.16%)
Mutual labels:  embeddings
Sensegram
Making sense embedding out of word embeddings using graph-based word sense induction
Stars: ✭ 209 (+1000%)
Mutual labels:  embeddings
Catalyst
🚀 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.
Stars: ✭ 224 (+1078.95%)
Mutual labels:  embeddings
Datastories Semeval2017 Task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis".
Stars: ✭ 184 (+868.42%)
Mutual labels:  embeddings
Vectorai
Vector AI — A platform for building vector based applications. Encode, query and analyse data using vectors.
Stars: ✭ 195 (+926.32%)
Mutual labels:  embeddings
Magnetloss Pytorch
PyTorch implementation of a deep metric learning technique called "Magnet Loss" from Facebook AI Research (FAIR) in ICLR 2016.
Stars: ✭ 217 (+1042.11%)
Mutual labels:  embeddings
Entity2rec
entity2rec generates item recommendation using property-specific knowledge graph embeddings
Stars: ✭ 159 (+736.84%)
Mutual labels:  embeddings
img2vec-keras
Image to dense vector embedding. Clone of https://github.com/christiansafka/img2vec for Keras users
Stars: ✭ 36 (+89.47%)
Mutual labels:  embeddings
Food2vec
🍔
Stars: ✭ 199 (+947.37%)
Mutual labels:  embeddings
Cw2vec
cw2vec: Learning Chinese Word Embeddings with Stroke n-gram Information
Stars: ✭ 224 (+1078.95%)
Mutual labels:  embeddings
Vec4ir
Word Embeddings for Information Retrieval
Stars: ✭ 188 (+889.47%)
Mutual labels:  embeddings
Research2vec
Representing research papers as vectors / latent representations.
Stars: ✭ 192 (+910.53%)
Mutual labels:  embeddings
Kprn
Reasoning Over Knowledge Graph Paths for Recommendation
Stars: ✭ 220 (+1057.89%)
Mutual labels:  embeddings
Jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
Stars: ✭ 172 (+805.26%)
Mutual labels:  embeddings
Whatlies
Toolkit to help understand "what lies" in word embeddings. Also benchmarking!
Stars: ✭ 246 (+1194.74%)
Mutual labels:  embeddings
Cofactor
CoFactor: Regularizing Matrix Factorization with Item Co-occurrence
Stars: ✭ 160 (+742.11%)
Mutual labels:  embeddings
Cause
Code for the Recsys 2018 paper entitled Causal Embeddings for Recommandation.
Stars: ✭ 207 (+989.47%)
Mutual labels:  embeddings
word-embeddings-from-scratch
Creating word embeddings from scratch and visualize them on TensorBoard. Using trained embeddings in Keras.
Stars: ✭ 22 (+15.79%)
Mutual labels:  embeddings
simple elmo
Simple library to work with pre-trained ELMo models in TensorFlow
Stars: ✭ 49 (+157.89%)
Mutual labels:  embeddings
Deepehr
Chronic Disease Prediction Using Medical Notes
Stars: ✭ 220 (+1057.89%)
Mutual labels:  embeddings

Geometric Embedding Algorithm (GEM)

This is an implementation of Geometric Embedding Algorithm, a simple and robust non-parameterized approach for building sentence representations. See the paper for more details.

The work is done as a project for NLA course at Skoltech.

Example

from gem import SentenceEmbedder
from embeddings import get_embedding_matrix

sentences = ["We come from the land of the ice and snow",
            "From the midnight sun where the hot springs blow"]
            
embedding_matrix, vocab = get_embedding_matrix('glove.6B.300d.txt')
embedder = SentenceEmbedder(sentences, embedding_matrix, vocab)

embedded_sentences = embedder.gem(window_size=3, sigma_power=3)

Data used

Team

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].