neural-mt Goto Github PK

adaptive-span

Transformer training code for sequential tasks

alignment-scripts

Scripts to preprocess training and test data and to run fast_align and giza

attention_with_linear_biases

Code for the ALiBi method for transformer language models (ICLR 2022)

bert-nmt

data_diversification

Instruction to data diversification

deep-generative-models-for-natural-language-processing

DGMs for NLP. A roadmap.

explicit-sparse-transformer

code for Explicit Sparse Transformer

exposure-bias-hallucination-domain-shift

Introduction and scripts for ACL-2020 paper "On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation"

fairseq

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

fast-soft-sort

Fast Differentiable Sorting and Ranking

fast_align

Simple, fast unsupervised word aligner

good-translation-wrong-in-context

This is a repository with the data and code for the ACL 2019 paper "When a Good Translation is Wrong in Context: ..." and the EMNLP 2019 paper "Context-Aware Monolingual Repair for Neural Machine Translation"

gumbel-crf

Implementation of NeurIPS 20 paper: Latent Template Induction with Gumbel-CRFs

lite-transformer

[ICLR 2020] Lite Transformer with Long-Short Range Attention

literalness-per-sentence

Code for "Do GPTs Produce Less Literal Translations?"

longformer

Longformer: The Long-Document Transformer

loss_dropper

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.

meta_seq2seq

Compositional generalization through meta sequence-to-sequence learning

mixture-of-experts

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

monoses

Unsupervised Statistical Machine Translation

mosesdecoder

Moses, the machine translation system

muse

A library for Multilingual Unsupervised or Supervised word Embeddings

neuralcodesum

Official implementation of our ACL 2020 paper on Source Code Summarization.

notebooks

Some notebooks for NLP

openplayground

An LLM playground you can run on your laptop

progressive-generation

prophetnet

ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training https://arxiv.org/pdf/2001.04063.pdf

python-word-error-rate

Calculates the word error rate of two strings, and the result is written into beautify html

sparse_recovery

noiseless/nonnegative sparse recovery and feature retrieval via compressed sensing