HA-Transformer / MATLinks
The implementation of multi-branch attentive Transformer (MAT).
☆33Updated 5 years ago
Alternatives and similar repositories for MAT
Users that are interested in MAT are comparing it to the libraries listed below
Sorting:
- Curriculum Learning related papers and materials☆53Updated 5 years ago
- ☆22Updated 4 years ago
- Code for paper "Continual and Multi-Task Architecture Search (ACL 2019)"☆41Updated 6 years ago
- DisCo Transformer for Non-autoregressive MT☆77Updated 3 years ago
- PyTorch Implementation of NeurIPS 2020 paper "Learning Sparse Prototypes for Text Generation"☆22Updated 4 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 3 years ago
- Source code for "Efficient Training of BERT by Progressively Stacking"☆113Updated 6 years ago
- Source code for "Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation"☆18Updated 6 years ago
- PyTorch implementation of Transformer-based Neural Machine Translation☆78Updated 3 years ago
- A dual learning toolkit developed by Microsoft Research☆73Updated 2 years ago
- ☆28Updated 4 years ago
- ☆32Updated 4 years ago
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆127Updated 4 years ago
- Language Model Baselines for PyTorch☆41Updated 5 years ago
- A Toolkit for Training, Tracking, Saving Models and Syncing Results