machelreid Goto Github PK

abci-utils

Utils for ABCI (https://abci.ai/) cluster

afromt

Code for the EMNLP 2021 Paper "AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages" by Machel Reid, Junjie Hu, Graham Neubig, Yutaka Matsuo

can-wikipedia-help-offline-rl

Official code for "Can Wikipedia Help Offline Reinforcement Learning?" by Machel Reid, Yutaro Yamada and Shixiang Shane Gu

conference-acceptance-rate

Statistics of acceptance rate for the main AI conference

diffuser

DiffusER: Discrete Diffusion via Edit-based Reconstruction (Reid, Hellendoorn & Neubig, 2022)

editpro

Learning to Model Editing Processes

fairseq

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

flores

Facebook Low Resource (FLoRes) MT Benchmark

hiddic

A library/pipeline for building and training NLP models

language-style-transfer

lewis

Official code for LEWIS, from: "LEWIS: Levenshtein Editing for Unsupervised Text Style Transfer", ACL-IJCNLP 2021 Findings by Machel Reid and Victor Zhong

m2d2

M2D2: A Massively Multi-domain Language Modeling Dataset (EMNLP 2022) by Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer

mit6.00.1x

obsidian-translations

Help translate Obsidian into your language.

paradise

PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining (NAACL 2022), Machel Reid and Mikel Artetxe

rakutenhack-1

SuperNannies repo for RakutenHackathon 2018

subformer

The code for the Subformer, from the EMNLP 2021 Findings paper: "Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers", by Machel Reid, Edison Marrese-Taylor, and Yutaka Matsuo

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

twitter-search-api

Twitter Search API (open-source). Project developed as part of internship with Numada Lab with Professor Muneyoshi Numada at the University of Tokyo

vcdm

The official implementation for "VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling", EMNLP 2020

xlm

PyTorch original implementation of Cross-lingual Language Model Pretraining.