paper-NLP's repositories
NSP-BERT
The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"
StructurePrediction18
Code for doing Argument Structure Prediction using Residual Networks and (almost) without symbolic features
ASM
( NeurIPS 2020 ) Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
Automated-Fact-Checking-Resources
Links to conference/journal publications in automated fact-checking (resources for the TACL21 paper).
CLKD
Cross-lingual Knowledge Distillation framework
CrossFake
A cross-lingual COVID-19 fake news dataset
CrossFit
Code for paper "CrossFit :weight_lifting:: A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)
Datawhale_notes-
记录我参加的Datawhale组队学习,包括笔记和习题解答
DSRAN
Code for journal paper "Learning Dual Semantic Relations with Graph Attention for Image-Text Matching", TCSVT, 2020.
GraphLoG
Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).
Graphormer
Graphormer is a deep learning package that allows researchers and developers to train custom models for molecule modeling tasks. It aims to accelerate the research and application in AI for molecule science, such as material discovery, drug discovery, etc.
icann2021-unsupervised-language-adaptation
Code for the ICANN 2021 paper "Improving Transfer Learning in Unsupervised Language Adaptation"
LOANT
code for NAACL 2021 paper "Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection"
nlp4if-2021
Cross-lingual misinformation detection
P-tuning-v2
An optimized prompt tuning strategy comparable to fine-tuning across model scales and tasks.
PCS-FUDA
Official implementation of PCS in essay "Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation"
rumor-fake-news-papers
🚨 Rumor, Fake News, Misinformation Papers
scrapy-aaai-2021
AAAI 2021 CRAWER
StyleAttack
Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"
Transliteration-Hindi-Malayalam
Cross-Lingual Text Classification of TransliteratedHindi and Malayalam
unify-parameter-efficient-tuning
Implementation of paper "Towards a Unified View of Parameter-Efficient Transfer Learning"
XLM
PyTorch original implementation of Cross-lingual Language Model Pretraining.
xtreme
XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.