Kevin Duh's repositories
sockeye-recipes
Training scripts and recipes for Sockeye Neural Machine Translation toolkit
nlp-course
Natural Language Processing course at Johns Hopkins University (Course # 601.465/665)
sockeye-recipes2
Training scripts and recipes for the Sockeye Neural Machine Translation (NMT) toolkit v2
sockeye-recipes3
Training recipes and AutoML for the Sockeye Neural Machine Translation (NMT) toolkit v3
iwslt22-dialect
IWSLT 2022 Dialectal Speech Translation Shared Task
word2vec-pp
Modifications of word2vec
ARR-pctools
Simple scripts for program chairs of ARR/OpenReview reviewing
cedr
Code for CEDR: Contextualized Embeddings for Document Ranking, accepted at SIGIR 2019.
CLIReval
CLIReval is an open-source toolkit that evaluates the quality of MT outputs in the context of a CLIR system, without the need for any actual CLIR dataset.
compare-mt
A tool for holistic analysis of language generations systems
DeepLearningIntro
Lecture slides on deep learning
elastic4clir
ElasticSearch package for Cross-lingual Information Retrieval
hyperband-sim
Hyperband Simulation for Hyperparameter Optimization
language-model-stats
Quick reference for large pre-trained language models
nematus-train
scripts and configuration files for Edinburgh neural MT submission to WMT 16 shared translation task
OpenNIR
An end-to-end neural ad-hoc ranking pipeline.
subword-nmt
Subword Neural Machine Translation
yanmtt
Yet Another Neural Machine Translation Toolkit