lancopku / Prime
A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.
☆87Updated last year
Related projects ⓘ
Alternatives and complementary repositories for Prime
- ICLR2019, Multilingual Neural Machine Translation with Knowledge Distillation☆70Updated 4 years ago
- Cascaded Text Generation with Markov Transformers☆128Updated last year
- ☆83Updated 5 years ago
- This code repository presents the pytorch implementation of the paper “Implicit Deep Latent Variable Models for Text Generation”(EMNLP 20…☆55Updated 2 years ago
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆125Updated 3 years ago
- Source code to reproduce the results in the ACL 2019 paper "Syntactically Supervised Transformers for Faster Neural Machine Translation"☆82Updated 2 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 2 years ago
- Source code for "Efficient Training of BERT by Progressively Stacking"☆112Updated 5 years ago
- ☆32Updated 3 years ago
- DisCo Transformer for Non-autoregressive MT☆78Updated 2 years ago
- ☆21Updated 4 years ago
- code for paper "Improving Sequence-to-Sequence Learning via Optimal Transport"☆68Updated 5 years ago
- Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"☆47Updated 2 years ago
- ☆120Updated 5 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 3 years ago
- PyTorch implementation of A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text (EMNLP 2019)☆47Updated 4 years ago
- ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation☆24Updated 4 years ago
- Variational Transformers for Diverse Response Generation☆82Updated 3 months ago
- a Pytorch implementation of the Reformer Network (https://openreview.net/pdf?id=rkgNKkHtvB)☆54Updated last year
- Code for "Understanding and Improving Layer Normalization"☆46Updated 4 years ago
- ☆17Updated 2 years ago
- Code for "A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations" (NAACL 2019)☆68Updated 3 years ago
- ☆13Updated 5 years ago
- LaNMT: Latent-variable Non-autoregressive Neural Machine Translation with Deterministic Inference☆79Updated 3 years ago
- ☆22Updated 3 years ago
- ☆47Updated 4 years ago
- This repo provides the code for the ACL 2020 paper "Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEnco…☆52Updated 3 years ago
- Source code for the paper "Multilingual Neural Machine Translation with Soft Decoupled Encoding"☆29Updated 3 years ago
- Re-implement "QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension"☆120Updated 6 years ago
- Code for EMNLP 2019 paper "Attention is not not Explanation"☆57Updated 3 years ago