Raymond Hendy's repositories
constrained-levt
Lexically Constrained Neural Machine Translation with Levenshtein Transformer
bert-sentencepiece
TensorFlow code and pre-trained models for BERT
fairseq-laser
My implementation of LASER architecture in Fairseq
lang-8-process
Lang-8 preprocessing scripts
semantic-multi
Code repo for ACL'17
char-rnn-truecase
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
pytorch-char-rnn-truecase
Character-level LSTM for Truecasing in PyTorch
bert-japanese
BERT with SentencePiece for Japanese text.
Mask-Predict
A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.
mlx-gpt
GPT-2 implementation in MLX
mosesdecoder
Moses, the machine translation system
product-translator
Product title translation
pytorch-pretrained-BERT
đź“–The Big-&-Extending-Repository-of-Transformers: Pretrained PyTorch models for Google's BERT, OpenAI GPT & GPT-2, Google/CMU Transformer-XL.
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
smt-spell-check
Building a spell-checker based on SMT
sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
statnlp-sp-neural
Code repo for AAAI'17