Thang Luong's Projects
Apollocaffe - Dynamic networks with caffe -
Train bilingual embeddings as described in our NAACL 2015 workshop paper "Bilingual Word Representations with Monolingual Quality in Mind". Besides, it has all the functionalities of word2vec with added features and code clarity. See README for more info.
The Earleyx parser was originated from Roger Levy's prefix parser, but has evolved significantly. Earleyx can generate Viterbi parses and perform rule estimation (Expectation-Maximization and Variational Bayes). The parser also implements the scaling approach as described in my TACL'13 paper which speeds up parsing time and allows for parsing long sentences (with restricted grammars).
Train deep neural language models as described in this paper "Deep Neural Language Models for Machine Translation" http://www.aclweb.org/anthology/K/K15/K15-1031.pdf . We don't claim that this is a fast implementation but was sufficient for us to obtain consistent gains in real translation tasks.
State-of-the-art Neural Machine Translation Codebase including Hybrid Word-character Models
Code to train state-of-the-art Neural Machine Translation systems.
Thang Luong's thesis on Neural Machine Translation