graehl Goto Github PK

.emacs.d

My new emacs config, inspired by @emacsrocks

ag.el

An Emacs frontend to ag, ("the silver searcher" ack replacment)

autopair-el

Automagically pair braces and quotes like TextMate (fork version)

bert

TensorFlow code and pre-trained models for BERT

bimpm

BiMPM: Bilateral Multi-Perspective Matching for Natural Language Sentences

boost

contributions to boost (each in its own branch - see branches dropdown. dynamic_bitset and object_pool so far). master follows boost svn trunk.

brew

:beer: The missing package manager for OS X

caffe

Caffe: a fast open framework for deep learning.

carmel

finite-state toolkit, EM and Bayesian (Gibbs sampling) training for FST and context-free derivation forests

cdec

Decoder, aligner, and model optimizer for statistical machine translation and other structured prediction models based on (mostly) context-free formalisms

char-rnn

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

cld2

Automatically exported from code.google.com/p/cld2

cnn-for-sentence-classification-in-keras

Convolutional Neural Networks for Sentence Classification in Keras

cnn-text-classification-tf

Convolutional Neural Network for Text Classification in Tensorflow

cnpy

library to read/write .npy and .npz files in C/C++

convsent

The training code for the EMNLP 2017 paper "Learning Generic Sentence Representations Using Convolutional Neural Networks"

corpora

cppcheck

static analysis of C/C++ code

cppzmq

C++ binding for 0MQ

deep-siamese-text-similarity

Tensorflow based implementation of deep siamese LSTM network to capture phrase/sentence similarity using character embeddings

dotfiles

:wrench: .files, including ~/.osx — sensible hacker defaults for OS X

eflomal

Efficient Low-Memory Aligner

efmaral

Efficient Markov Chain word alignment

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit

fast_align

Simple, fast unsupervised word aligner

gitcredit

create git sub-repository with per-author initial commits (hiding history but keeping authors)

gitsum

basic darcsum feelalike for Git

giza-pp

GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.

google-research

Google AI Research

graehl.github.io

graehl.org