ankit-cliqz Goto Github PK

annoy

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

annoy2

cnn-for-sentence-classification-in-keras

Convolutional Neural Networks for Sentence Classification in Keras

code_search

Code For Medium Article: "How To Create Natural Language Semantic Search for Arbitrary Objects With Deep Learning"

dl4nlp

Deep Learning for NLP resources

dnn_page_vectors

Deep Neural Network Based Distributed Representation of Web Page Content

dtm

Dynamic Topic Model (based upon code released by David Blei at http://www.cs.princeton.edu/~blei/topicmodeling.html)

fairing

Python SDK for building, training, and deploying ML models

fasttext

Library for fast text representation and classification.

keyvi

keyvi is a key value index, an in-memory FST-based data structure, optimized for size and lookup performance.

kubernetes-helm-chart-cassandra

Kubernetes Helm Chart for Cassandra

page_vectors

Distributed Representation of Web Page Content (Customized Selection) based on Paragraph Vectors

playground

Playground for university

query_embeddings

"Query Embeddings", which are an extension of word embeddings, but are useful to understand similarity between queries, learned by the neural network algorithms in an unsupervised fashion. The overall goal is to improve relevance of pages returned for the unseen queries sent to our search engine. Area: Deep Learning for Information Retrieval.

sense2vec

Use spaCy to go beyond vanilla word2vec

seq2seq

Sequence to Sequence Learning with Keras

shiva

Side By Side Search Result Comparison Tool

tensorflow_fasttext

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

theano_exercises

Exercises for my tutorials on Theano

vsts-docs

This repo is the home of the official Azure DevOps documentation for Microsoft. GitHub Issues filed in this repository should be for problems with the documentation.

word2vec

Automatically exported from code.google.com/p/word2vec