zhuohan123 / macaron-net
Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"
☆148Updated 5 years ago
Alternatives and similar repositories for macaron-net:
Users that are interested in macaron-net are comparing it to the libraries listed below
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆128Updated 3 years ago
- Source code for "Efficient Training of BERT by Progressively Stacking"☆112Updated 5 years ago
- Generative Flow based Sequence-to-Sequence Toolkit written in Python.☆244Updated 5 years ago
- ☆119Updated 6 years ago
- Code for the ICML'20 paper "Improving Transformer Optimization Through Better Initialization"☆88Updated 4 years ago
- A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.☆86Updated last year
- Implementation of Stochastic Beam Search using Fairseq☆100Updated 5 years ago
- PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"☆268Updated 3 years ago
- ☆216Updated 4 years ago
- Adaptive Softmax implementation for PyTorch☆80Updated 5 years ago
- Code for "Language GANs Falling Short"☆59Updated 4 years ago
- Non-autoregressive Neural Machine Translation (not a full version)☆71Updated 2 years ago
- This code repository presents the pytorch implementation of the paper “Implicit Deep Latent Variable Models for Text Generation”(EMNLP 20…☆54Updated 3 years ago
- PyTorch implementation of Transformer-based Neural Machine Translation☆77Updated 2 years ago
- Cascaded Text Generation with Markov Transformers☆129Updated 2 years ago
- Implementation of Sparsemax activation in Pytorch☆159Updated 4 years ago
- Codes for "Towards Binary-Valued Gates for Robust LSTM Training".☆76Updated 6 years ago
- Non-Monotonic Sequential Text Generation (ICML 2019)☆72Updated 5 years ago
- Code for "Understanding and Improving Layer Normalization"☆46Updated 5 years ago
- Implementation of Universal Transformer in Pytorch☆259Updated 6 years ago
- DisCo Transformer for Non-autoregressive MT☆77Updated 2 years ago
- Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve exis…☆250Updated 3 years ago
- Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.☆115Updated 4 years ago
- Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"☆168Updated 6 years ago
- A Toolkit for Training, Tracking, Saving Models and Syncing Results☆60Updated 5 years ago
- NeurIPS 2019 - Learning Data Manipulation for Augmentation and Weighting☆109Updated 4 years ago
- LaNMT: Latent-variable Non-autoregressive Neural Machine Translation with Deterministic Inference☆79Updated 3 years ago
- ☆83Updated 5 years ago
- MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders☆23Updated 5 years ago
- [EMNLP'19] Summary for Transformer Understanding☆53Updated 5 years ago