Data augmentation for NLP, presented at EMNLP 2019

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

A data augmentations library for audio, image, text, and video.

Data augmentation for NLP

List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.

TextAugment: Text Augmentation Library

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Clone of COCO API - Dataset @ https://cocodataset.org/ - with changes to support Windows build and python3

Evaluating Visual Fidelity of Image Descriptions

MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance

BLEURT is a metric for Natural Language Generation based on transfer learning.

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

Automatic metrics for GEM tasks

Support extracting BUTD features for NLVR2 images.

Python 3 support for the MS COCO caption evaluation tools

CLIPScore EMNLP code

Code for ViLBERTScore in EMNLP Eval4NLP

BARTScore: Evaluating Generated Text as Text Generation

Measure the diversity of image descriptions, repository for our COLING 2018 paper.

Universal Python binding for the LMDB 'Lightning' Database

Python ODBC bridge

A dataset of crowdsourced ratings for machine-generated image captions

PyTorch bottom-up attention with Detectron2

Code for GHA (ACCV2018)

Code for Neural Motifs: Scene Graph Parsing with Global Context (CVPR 2018)

Meshed-Memory Transformer for Image Captioning. CVPR 2020