jack57lee / Diversify-MHALinks
EMNLP 2018: Multi-Head Attention with Disagreement Regularization; NAACL 2019: Information Aggregation for Multi-Head Attention with Routing-by-Agreement
☆21Updated 5 years ago
Alternatives and similar repositories for Diversify-MHA
Users that are interested in Diversify-MHA are comparing it to the libraries listed below
Sorting:
- Code for "Understanding and Improving Layer Normalization"☆46Updated 5 years ago
- ☆84Updated 5 years ago
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆128Updated 4 years ago
- The implementation of multi-branch attentive Transformer (MAT).☆33Updated 5 years ago
- Source code for "Efficient Training of BERT by Progressively Stacking"☆113Updated 6 years ago
- Differentiable Product Quantization for End-to-End Embedding Compression.☆63Updated 2 years ago
- Leveraging Local and Global Patterns for Self-Attention Networks☆12Updated 6 years ago
- Efficient Neural Interaction Functions Search for Collaborative Filtering☆18Updated 5 years ago
- Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"☆148Updated 6 years ago
- Reproduce the results of paper "Compressing Word Embeddings via Deep Compositional Code Learning" accepted ICLR 2018☆24Updated 7 years ago
- 基于Transformer的单模型、多尺度的VAE模型☆57Updated 4 years ago
- A PyTorch implementation of the paper - "Synthesizer: Rethinking Self-Attention in Transformer Models"☆73Updated 2 years ago
- Implementation of SetRank in SIGIR 2020☆50Updated 5 years ago
- This repo provides the code for the ACL 2020 paper "Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEnco…☆55Updated 4 years ago
- Code for ACL2018 paper "Learn How to Actively Learn: An Imitation Learning Approach"☆10Updated 6 years ago
- Codes for "Towards Binary-Valued Gates for Robust LSTM Training".☆74Updated 7 years ago
- Unsupervised Learning of Transferable Relational Graphs☆69Updated 6 years ago
- ☆50Updated 2 years ago
- Repository for ACL 2019 paper☆72Updated 6 years ago
- A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.☆86Updated 2 years ago
- NeurIPS 2019 - Learning Data Manipulation for Augmentation and Weighting☆110Updated 5 years ago
- Visualization for simple attention and Google's multi-head attention.☆68Updated 7 years ago
- ICLR2019, Multilingual Neural Machine Translation with Knowledge Distillation☆70Updated 5 years ago
- The implementation of Meta-LSTM in "Meta Multi-Task Learning for Sequence Modeling." AAAI-18☆33Updated 7 years ago
- A dual learning toolkit developed by Microsoft Research☆71Updated 2 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 3 years ago
- Code for the article "Automatic Temperature Control for Neural Machine Translation" (EMNLP 2018)☆14Updated 6 years ago
- Code for ACL'19 "Few-Shot Representation Learning for Out-Of-Vocabulary Words"☆55Updated 5 years ago
- Sampled Softmax Implementation for PyTorch☆44Updated 7 years ago
- Code implementation of paper Towards A Deep and Unified Understanding of Deep Neural Models in NLP☆73Updated 6 years ago