hieuhoang

parSentExtract

A BiRNN framework implemented in Python and TensorFlow to extract parallel sentences from aligned comparable corpora.

ALMA

State-of-the-art LLM-based translation models.

amun

Stand-alone C++ decoder for RNN-based NMT models. Can decode with default models from Marian and Nematus.

amunmt-regression-tests

argspp

An argument-parsing library for C++.

azure-quickstart-templates

Azure Quickstart Templates

bitextor

Bitextor generates translation memories from multilingual websites

docent

Document-Level Local Search Decoder for Phrase-Based Statistical Machine Translation

faiss

A library for efficient similarity search and clustering of dense vectors.

fast_align

Simple, fast unsupervised word aligner

FasterTransformer

Transformer related optimization, including BERT, GPT

fpga

ggks-multiSelect

HashingDeepLearning

Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"

hieuhoang.github.io

lattice_align

lxmls-toolkit

Machine Learning applied to Natural Language Processing Toolkit used in the Lisbon Machine Learning Summer School

Machine-Learning-Collection

PyTorch Tutorials, TensorFlow Tutorials and Machine Learning Algorithms

marian-dev

Fast Neural Machine Translation in C++ - development repository

marian-xml

moses-regression-tests

Regression test data and test cases

nplm

Fork of http://nlg.isi.edu/software/nplm/ for threadsafety and efficiency.

papers

odds and sods for sharing and collaboration

salm

snowball

Snowball compiler and stemming algoritms

Sugarizer

A taste of the Sugar learning platform on any device

wmt16-scripts

scripts and configuration files for Edinburgh neural MT submission to WMT 16 shared translation task