robustgen

perfect

PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models

robustness_metrics

numerizer

A Python module to convert natural language numerics into ints and floats.

SentAugment

SentAugment is a data augmentation technique for NLP that retrieves similar sentences from a large bank of sentences. It can be used in combination with self-training and knowledge-distillation, or for retrieving paraphrases.

vision_transformer

bleurt

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

fast-transformers

Pytorch library for fast transformer implementations

DuaLUG

The implementation of the papers on dual learning of natural language understanding and generation. (ACL2019,2020; Findings of EMNLP 2020)

KGPT

Code and Data for EMNLP2020 Paper "KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation"

sparse_text_generation

lookahead

Implementation for the Lookahead Optimizer.

injecting_numeracy

The accompanying code for "Injecting Numerical Reasoning Skills into Language Models" (Mor Geva*, Ankit Gupta* and Jonathan Berant, ACL 2020).

HFC

Implementation for the paper (CVPR Oral): High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks

loss_dropper