ryancotterell

arabic_dialect_annotation

arabic dialect annotation LREC paper

Choban

Mechanical Turk Widget Set for Pyjamas

HITnRun

Yet Another MTurk Toolkit

em-for-dpps

Automatically exported from code.google.com/p/em-for-dpps

FlashWavRecorder

Simple flash file for recording audio and saving as a WAV

old-jhu

Repository for Machine Learning in Complex Domains (600.476) - Suchi Saria

csv-parser

A CSV Parser in C++ without any bells and whistles

deromanization

embedding-evaluation

Evaluation tool for word embeddings

expected-edit-distance

Expected edit distance implementation using OpenFst tools

flect

Statistical morphology generation models

fstrain

A toolkit for training finite-state models

HindiASRHit

Hindi ASR Hit

hltdi-morphology

Mirror Repository for ParaMorfo, HornMorpho, AntiMorfo, and MorfoMelayu

hpstr-jekyll-theme

A Jekyll theme with some tumble-log tendencies.

hyperwords

Fork of https://bitbucket.org/omerlevy/hyperwords

kenlm

KenLM: Faster and Smaller Language Model Queries

lltk

The Language Learning Toolkit (LLTK) performs a variety of tasks useful for (human) language learning.

MBMP-morphological-parser

A memory-based morphological parser for Python

ml-project

morpho-learner

A theory-driven morphological parser

pyfst

A Python interface to OpenFst

pylbfgs

Python/Cython wrapper for liblbfgs

pypyenv

Easily install PyPy in a virtualenv without touching CPython.

Resume-1

Because I need version tracking for my resume

stochasticedit

Stochastic edit distance implementation using OpenFst

svdmi

Common pre-processing in NLP such as PPMI computation, SVD-based dimensionality reduction, and PLSR-based distribution prediction.

vpyp

Pitman-Yor processes in python

word2vec

This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently used in many natural language processing applications and for further research.

word2vecpy

Python implementation of CBOW and skip-gram word vector models, and hierarchical softmax and negative sampling learning algorithms