Named Entity Recognition (NER) with different combinations of BiGRU, Self-Attention and CRF

https://arxiv.org/pdf/1909.04054

A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

a library for named entity recognition developed by UF HOBI NLP lab featuring SOTA algorithms

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

Simple pytorch implementation of focal loss

The repo contains the code of the ACL2020 paper `Dice Loss for Data-imbalanced NLP Tasks`

A practical implementation of GradNorm, Gradient Normalization for Adaptive Loss Balancing, in Pytorch

The repository for the code of the UltraFastBERT paper

Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

This repository contains demos I made with the Transformers library by HuggingFace.