Chris Dyer's lab @ LTI/CMU

dynet

DyNet: The Dynamic Neural Network Toolkit

fast_align

Simple, fast unsupervised word aligner

dynet_tutorial_examples

Tutorial on "Practical Neural Networks for NLP: From Theory to Code" at EMNLP 2016

stack-lstm-ner

NER system based on stack LSTMs

lstm-parser

Transition-based dependency parser based on stack LSTMs

rnng

Recurrent neural network grammars

wikipedia-parallel-titles

Tools for extracting parallel corpora from article titles across languages in Wikipedia

language-universal-parser

cnn-v1

Legacy version of CNN neural net toolkit (now called dynet)

clab-autodiff-examples

Examples of using the adept autodifferentiation library for standard NLP learning problems

lstm-parser-with-beam-search

knowledge

lstm-parser-with-morphology

att-coref

lstm-parser-dynamic

sp2016.11-731

Master repository for CMU Machine Translation (11-731) in Spring 2016

mkcls

Franz Och's mkcls

gv-crawl

Global Voices bitext crawler

sp2014.11-731

Master repository for Machine Translation (11-731) in Spring 2014

ark-tweet-nlp

CMU ARK Twitter Part-of-Speech Tagger

cuda-teaching

Some CUDA examples

pyfst

A Python interface to OpenFst

sp2015.11-731

Master repository for CMU Machine Translation (11-731) in Spring 2015

aggregate-sp2014-11731

Aggregation of student repositories

aggregate-sp2015-11731

aggregate-sp2015-11731

aggregate-sp2016-11731

aggregator repository for student submissions

clab-scalable-cca

dwl

discriminative word lexicon built on top of cnn

minerva

Minerva: a fast and flexible tool for deep learning. It provides ndarray programming interface, just like Numpy. Python bindings and C++ bindings are both available. The resulting code can be run on CPU or GPU. Multi-GPU support is very easy. Please refer to the examples to see how multi-GPU setting is used.

UD_Hebrew-HTB

Hebrew Universal Dependencies Treebank