turian
Deep learning, NLP, audio AI 🧑🔬 Postdoc under Bengio 🧑🎓 ACL 10 Year Test of Time Award (lead author) 🌟 when art meets science... 👩🎤
Berlin + New York
Pinned Repositories
common
Common Python library, especially for text processing and controlling experimental runs
crfchunking-with-wordrepresentations
Train a CRF for syntactic chunking (CoNLL2000), and use word representations
kea-service
KEA 5.0 (keyphrase extraction software), modified to be an XML-RPC service
neural-language-model
Implementation of neural language models, in particular Collobert + Weston (2008) and a stochastic margin-based version of Mnih's LBL.
pytextpreprocess
Preprocess text for NLP (tokenizing, lowercasing, stemming, sentence splitting, etc.)
random-indexing-wordrepresentations
Induce word representations using random indexing (RI)
save-my-browser-tabs
Extension for Mozilla Firefox and Google Chrome to save all of your open tabs to a text file (window/tab index, URL and title of each tab)
stanford-pos-tagger-service
XML-RPC version of the Stanford POS tagger
textSNE
2-d visualization of high-dimensional input: Python code for rendering t-SNE code with text labels for each point
topia.termextract
Updates to Zope's keyphrase extractor (forked from 1.1.0)
turian's Repositories
turian/kea-service
KEA 5.0 (keyphrase extraction software), modified to be an XML-RPC service
turian/pytextpreprocess
Preprocess text for NLP (tokenizing, lowercasing, stemming, sentence splitting, etc.)
turian/random-indexing-wordrepresentations
Induce word representations using random indexing (RI)
turian/stanford-pos-tagger-service
XML-RPC version of the Stanford POS tagger
turian/pyrandomprojection
Random projection library for Python, converting a dictionary to low-dimensional numpy matrix
turian/textrank
Java implementation of the TextRank algorithm by Mihalcea, et al. http://lit.csci.unt.edu/index.php/Graph-based_NLP
turian/donatefaces
Extract faces from video clips; generate training data for pose-invariant face features
turian/py80legsformat
In Python, read the .80 file format, for 80legs web crawl results.
turian/fatfreecrm-ec2
Deploy FatFree CRM on EC2
turian/scikits.learn.recipes
Recipes for scikits.learn
turian/django-instantmessage
IM-like application for Pinax social networks (Django), that allow you to see which friends are online and chat them
turian/flickorpus
flickorpus collects an image and tag corpus from flickr.
turian/osqa
OSQA branch, with some fixes
turian/simple-twitter-similarity
Didactic example of information retrieval, computing the similarity of two twitter users
turian/biased-text-sample
Perform a biased sample of text data
turian/osqa-install-webfaction
Install OSQA on webfaction
turian/pycrowdflower
Python code for accessing the CrowdFlower API
turian/wikiprep-esa
ESA implementation using Wikiprep output
turian/wikiprep-postprocess
Postprocess XML output from wikiprep (Wikipedia preprocessor) into JSON
turian/DeepANN-sparse
Fork of Xavier's code, for sparse sampling reconstruction [Theano based deep ANN learning code]
turian/fabricrecipes
fabric recipes, primarily for deploying Ubuntu and EC2 instances.
turian/dmoz-parser
Dmoz RDF parser
turian/osqa-jsmath
jsMath support for OSQA
turian/pyshortstringcompression
Compress short strings, using the Huffman algorithm.
turian/python-SimpleXMLRPCServer-permissive
A permissive version of the Python SimpleXMLRPCServer, which can correct errant XML input from the client.
turian/search-autocomplete
Javascript autocomplete, with MySQL/PHP backend
turian/vworker-select-all-workers-firefox-extension
Firefox extension to select all workers in vWorker search results page
turian/askbot-devel
ASKBOT is a StackOverflow-like Q&A forum, based on CNPROG.
turian/django-lazysignup
django-lazysignup is a package designed to allow users to interact with a site as if they were authenticated users, but without signing up. At any time, they can convert their temporary user account to a real user account.
turian/grab-wikipedia-abstracts
Grab all Wikipedia abstracts, in all languages