protonish

cipherdaug-nmt

Official code for the paper CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation published at ACL 2022 main conference.

fairseq-cipherdaug

A fairseq fork with breaking changes for CipherDAug nmt.

ParaNMT

Using Neural Machine Translation to extract multilingual paraphrases

sentence-completion

cloud-scripts

cvocp

Clustering with the OCP

datasets

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

decipher_symbol_recurrence

Data described in the paper "Decipherment as Regression: Solving Historical Substitution Ciphers by Learning Symbol Recurrence Relations"

deeplearning-papernotes

Summaries and notes on Deep Learning research papers

dist_tuto.pth

PyTorch Distributed Tutorial

fairseq-1

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fairseq_multi_fix

Code and Data release for "Improving Multilingual Translation by Representation and Gradient Regularization" (Yang et al. EMNLP 2021)

Head-first-Chinese-text-segmentation

Head first Chinese text segmentation

itst

itst

jackal

A very lightweight & responsive theme for Jekyll

metaseq

Repo for external large-scale work

mma_runs

mma runs. Progress Tracker: https://trello.com/b/vjd80del/iwslt-23

monotonic_multihead_attention

multirep_analysis

Scripts to analyse multilingual embeddings

nan-mt

NLP-fiddles

test

NumpyDL

Deep Learning Library. For education. Based on pure Numpy. Support CNN, RNN, LSTM, GRU etc.

PaperNotes

My notes on some Deep Learning papers

protonish.github.io

My academic homepage

proxy-a-distance

Proxy A-Distance algorithm for measuring domain disparity in parallel corpora

pytorch-lightning-conference-seed

Pytorch Lightning code guideline for conferences

rebiber

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

snippets

Miscellaneous python snippets

speech_scripts

thesis

Thang Luong's thesis on Neural Machine Translation