KMnP / can
🤔 When in Doubt: Improving Classification Performance with Alternating Normalization [Findings of EMNLP2021]
☆14Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for can
- 基于Transformer的单模型、多尺度的VAE模型☆53Updated 3 years ago
- 简单的挖矿病毒查杀脚本☆16Updated 2 years ago
- Source code for NAACL 2021 paper "TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference"☆44Updated 2 years ago
- reformer-pytorch中文版本,简单高效的生成模型。类似GPT2的效果☆16Updated last year
- Official code for ICLR 2022 paper: "PoNet: Pooling Network for Efficient Token Mixing in Long Sequences".☆31Updated last year
- Python下shuffle几百G文件☆33Updated 3 years ago
- A small framework mimics PyTorch using CuPy or NumPy☆27Updated 2 years ago
- Implementation of "RankCSE: Unsupervised Sentence Representation Learning via Learning to Rank" (ACL 2023)☆46Updated 7 months ago
- This repository contains the code for the paper in Findings of EMNLP 2021: "EfficientBERT: Progressively Searching Multilayer Perceptron …☆32Updated last year
- Dataset for Findings of ACL 23 "VCSum: A Versatile Chinese Meeting Summarization Dataset"☆29Updated last year
- Code for "Mixed Cross Entropy Loss for Neural Machine Translation"☆20Updated 3 years ago
- SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples☆73Updated 2 years ago
- Official Code for 'EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification' - NAACL 2022☆23Updated 2 years ago
- huggingface ChineseBert Tokenizer☆15Updated 2 years ago
- ☆86Updated 4 years ago
- A visualizer to display attention weights on text☆23Updated 5 years ago
- [NAACL'22] TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning☆92Updated 2 years ago
- 中文AllenNLP教程(持续更新)☆14Updated 5 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 2 years ago
- Lion and Adam optimization comparison☆56Updated last year
- Code for EMNLP 2021 main conference paper "Dynamic Knowledge Distillation for Pre-trained Language Models"☆40Updated 2 years ago
- UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning☆69Updated 3 years ago
- some strategies for exposure bias in seq2seq☆18Updated 4 years ago
- pytorch版simcse无监督语义相似模型☆22Updated 3 years ago
- ☆18Updated 3 months ago
- [ACL‘20] Highway Transformer: A Gated Transformer.☆32Updated 2 years ago
- Source code for our EMNLP'21 paper 《Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning》☆56Updated 3 years ago
- A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck☆10Updated 2 years ago
- The repository for our EMNLP'20 paper SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup.☆43Updated 3 years ago