jack57lee / Diversify-MHA
EMNLP 2018: Multi-Head Attention with Disagreement Regularization; NAACL 2019: Information Aggregation for Multi-Head Attention with Routing-by-Agreement
☆19Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for Diversify-MHA
- Efficient Neural Interaction Functions Search for Collaborative Filtering☆18Updated 4 years ago
- Reproduce the results of paper "Compressing Word Embeddings via Deep Compositional Code Learning" accepted ICLR 2018☆23Updated 6 years ago
- Code for "Understanding and Improving Layer Normalization"☆46Updated 4 years ago
- The implementation of Meta-LSTM in "Meta Multi-Task Learning for Sequence Modeling." AAAI-18☆33Updated 6 years ago
- Code for the article "Automatic Temperature Control for Neural Machine Translation" (EMNLP 2018)☆13Updated 5 years ago
- PyTorch implementation for the paper Classification from Positive, Unlabeled and Biased Negative Data.☆19Updated last year
- Leveraging Local and Global Patterns for Self-Attention Networks☆12Updated 5 years ago
- ☆12Updated 5 years ago
- ☆83Updated 5 years ago
- ☆9Updated 5 years ago
- Comprehensive Information Integration Modeling Framework for Video Titling☆11Updated 4 years ago
- PyTorch implementation of the paper "Hyperbolic Interaction Model For Hierarchical Multi-Label Classification"☆48Updated 5 years ago
- ☆12Updated 5 years ago
- [ACL‘20] Highway Transformer: A Gated Transformer.☆32Updated 2 years ago
- Code and dataset for "Transfer Learning Between Related Tasks Using Expected Label Proportions"☆16Updated 5 years ago
- Code for the NeurIPS 2018 paper "On Controllable Sparse Alternatives to Softmax"☆22Updated 5 years ago
- Train, Test and Dev Splits for our AAAI'18 Paper☆16Updated 6 years ago
- Code for Interpretable Adversarial Perturbation in Input Embedding Space for Text, IJCAI 2018.☆42Updated 4 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 2 years ago
- Codes for <Kernelized Bayesian Softmax for Text Generation> in NeurIPS 2019☆17Updated 5 years ago
- 基于Transformer的单模型、多尺度的VAE模型☆53Updated 3 years ago
- ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation☆24Updated 4 years ago
- Implementation of SetRank in SIGIR 2020☆51Updated 4 years ago
- ☆21Updated 5 years ago
- Partial Codes and datasets for NeurIPS'19 "Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers"☆19Updated 5 years ago
- Tensorflow Source code for "Recurrently Controlled Recurrent Networks" (NIPS 2018)☆23Updated 6 years ago
- Discrete Optimization for Unsupervised Sentence Summarization with Word-Level Extraction☆19Updated 2 years ago
- Ouroboros: On Accelerating Training of Transformer-Based Language Models☆10Updated 5 years ago
- Code for paper "Interactive Machine Comprehension with Information Seeking Agents" -- public version☆23Updated 5 years ago