lancopku / Prime
A simple module consistently outperforms self-attention and Transformer model on main NMT datasets with SoTA performance.
☆86Updated last year
Alternatives and similar repositories for Prime:
Users that are interested in Prime are comparing it to the libraries listed below
- ICLR2019, Multilingual Neural Machine Translation with Knowledge Distillation☆70Updated 4 years ago
- ☆32Updated 3 years ago
- Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"☆128Updated 4 years ago
- Cascaded Text Generation with Markov Transformers☆129Updated 2 years ago
- ☆119Updated 6 years ago
- PyTorch implementation of Transformer-based Neural Machine Translation☆77Updated 2 years ago
- a Pytorch implementation of the Reformer Network (https://openreview.net/pdf?id=rkgNKkHtvB)☆53Updated 2 years ago
- Source code to reproduce the results in the ACL 2019 paper "Syntactically Supervised Transformers for Faster Neural Machine Translation"☆81Updated 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
- Neutron: A pytorch based implementation of Transformer and its variants.☆63Updated last year
- Code for "A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations" (NAACL 2019)☆67Updated 4 years ago
- ☆47Updated 6 years ago
- Meta learning for Neural Machine Translation☆41Updated 2 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 4 years ago
- Adaptive Softmax implementation for PyTorch☆80Updated 6 years ago
- DisCo Transformer for Non-autoregressive MT☆77Updated 2 years ago
- ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation☆25Updated 4 years ago
- Language Model Baselines for PyTorch☆42Updated 4 years ago
- ☆53Updated 4 years ago
- ☆13Updated 6 years ago
- Codes for "Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View"☆148Updated 5 years ago
- ☆83Updated 5 years ago
- Domain Adaptive Text Style Transfer, EMNLP 2019☆70Updated 5 years ago
- [ACL‘20] Highway Transformer: A Gated Transformer.☆32Updated 3 years ago
- PyTorch implementation of A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text (EMNLP 2019)☆48Updated 5 years ago
- Bi-Directional Block Self-Attention☆123Updated 6 years ago
- Non-autoregressive Neural Machine Translation (not a full version)☆71Updated 2 years ago
- Boolean Question Answering with multi-task learning and uses large LM embeddings like BERT, RoBERTa☆18Updated 5 years ago
- Encoder-Agnostic Adaptation for Conditional Language Generation☆79Updated 9 months ago
- Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"☆46Updated 2 years ago