nishiwen1214 / R-AT
Licence: MIT license
Regularized Adversarial Training
Stars: ✭ 19
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to R-AT
cmrc2019
A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (CMRC 2019)
Stars: ✭ 118 (+521.05%)
Mutual labels: bert
ERNIE-text-classification-pytorch
This repo contains a PyTorch implementation of a pretrained ERNIE model for text classification.
Stars: ✭ 49 (+157.89%)
Mutual labels: bert
beir
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
Stars: ✭ 738 (+3784.21%)
Mutual labels: bert
AliceMind
ALIbaba's Collection of Encoder-decoders from MinD (Machine IntelligeNce of Damo) Lab
Stars: ✭ 1,479 (+7684.21%)
Mutual labels: bert
Kaleido-BERT
(CVPR2021) Kaleido-BERT: Vision-Language Pre-training on Fashion Domain.
Stars: ✭ 252 (+1226.32%)
Mutual labels: bert
GEANet-BioMed-Event-Extraction
Code for the paper Biomedical Event Extraction with Hierarchical Knowledge Graphs
Stars: ✭ 52 (+173.68%)
Mutual labels: bert
bert attn viz
Visualize BERT's self-attention layers on text classification tasks
Stars: ✭ 41 (+115.79%)
Mutual labels: bert
neuro-comma
🇷🇺 Punctuation restoration production-ready model for Russian language 🇷🇺
Stars: ✭ 46 (+142.11%)
Mutual labels: bert
NLPDataAugmentation
Chinese NLP Data Augmentation, BERT Contextual Augmentation
Stars: ✭ 94 (+394.74%)
Mutual labels: bert
LAMB Optimizer TF
LAMB Optimizer for Large Batch Training (TensorFlow version)
Stars: ✭ 119 (+526.32%)
Mutual labels: bert
OpenUE
OpenUE是一个轻量级知识图谱抽取工具 (An Open Toolkit for Universal Extraction from Text published at EMNLP2020: https://aclanthology.org/2020.emnlp-demos.1.pdf)
Stars: ✭ 274 (+1342.11%)
Mutual labels: bert
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].