hoangcuong2011

nlp-util

Random utilities for NLP

awesome-transformer

A collection of transformer's guides, implementations and variants.

bookcorpus

Crawl BookCorpus

coref

BERT for Coreference Resolution

deep-shallow

DZip

Compression

fairseq_help_fix_bug

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

FP-Net

Feature Projection for Improved Text Classification

gender-debias

Adaptation datasets and scripts for the paper "Reducing gender bias in Neural Machine Translation as a domain adaptation problem" (ACL 2020)

hoangcuong2011.github.io

hypergraphs

Reference implementations of basic and advanced hypergraph algorithms.

JEM

Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"

keras-adabound

Keras implementation of AdaBound

keras-bert-1

A simple technique to integrate BERT from tf hub to keras

KerasDropconnect

An implementation of DropConnect Layer in Keras

language-style-transfer

mt_gender

Multi-News

Large-scale multi-document summarization dataset and code

NLP-progress

Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

nmt-keras

Neural Machine Translation with Keras

NN_compression

rouge

A full Python Implementation of the ROUGE Metric (not a wrapper)

sacreBLEU

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

sacremoses

Python port of Moses tokenizer, truecaser and normalizer

sockeye

Sequence-to-sequence framework with a focus on Neural Machine Translation based on PyTorch

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

translation_bias

Data and notebook for experiments in Hovy et al. (2020) https://www.aclweb.org/anthology/2020.acl-main.154.pdf

U2GNN

Unsupervised Universal Self-Attention Network for Graph Classification

udify

A single model that parses Universal Dependencies across 75 languages. Given a sentence, jointly predicts part-of-speech tags, morphology tags, lemmas, and dependency trees.

XenC

XenC: open-source data selection tool for NLP