archinetai / smart-pytorch
PyTorch – SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models.
☆59Updated 2 years ago
Related projects: ⓘ
- This repository contains the code for paper Prompting ELECTRA Few-Shot Learning with Discriminative Pre-Trained Models.☆45Updated 2 years ago
- [NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining☆120Updated last year
- ☆82Updated 3 years ago
- Source code for paper "Learning from Noisy Labels for Entity-Centric Information Extraction", EMNLP 2021☆55Updated 2 years ago
- ☆116Updated 2 years ago
- Implementation of Mixout with PyTorch☆73Updated last year
- ☆65Updated 2 years ago
- [EMNLP 2021] Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification☆125Updated last year
- Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations☆133Updated 3 months ago
- [EMNLP 2021] Improving and Simplifying Pattern Exploiting Training☆153Updated 2 years ago
- [EMNLP'21] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.☆75Updated 2 years ago
- Code from the paper "What do Models Learn from Question Answering Datasets?" (EMNLP 2020)☆54Updated 3 years ago
- code associated with ACL 2021 DExperts paper☆109Updated last year
- Code for EMNLP 2021 paper: "Is Everything in Order? A Simple Way to Order Sentences"☆41Updated last year
- ☆55Updated last year
- Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper☆50Updated last year
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆135Updated 2 years ago
- Code for the paper "True Few-Shot Learning in Language Models" (https://arxiv.org/abs/2105.11447)☆142Updated 2 years ago
- Implementation of Self-adjusting Dice Loss from "Dice Loss for Data-imbalanced NLP Tasks" paper☆105Updated 3 years ago
- [NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self…☆200Updated 2 years ago
- Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"☆290Updated last year
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated last year
- ☆70Updated 2 years ago
- The source code for the Cutoff data augmentation approach proposed in this paper: "A Simple but Tough-to-Beat Data Augmentation Approach …☆62Updated 3 years ago
- [NAACL'22] TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning☆91Updated 2 years ago
- Official PyTorch Implementation of SSMix (Findings of ACL 2021)☆60Updated 3 years ago
- source code for paper: WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach.☆56Updated 3 years ago
- Long-context pretrained encoder-decoder models☆95Updated last year
- This repo supports various cross-lingual transfer learning & multilingual NLP models.☆91Updated last year
- PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction with Language Models, EMNLP 22. https://arxi…☆98Updated 7 months ago