samuki / reinforce-joey
This is a fork of the awesome Joey-NMT with Reinforcement Learning algorithms like Policy Gradient, MRT and Advantage Actor Critic.
☆26Updated last year
Related projects: ⓘ
- LaNMT: Latent-variable Non-autoregressive Neural Machine Translation with Deterministic Inference☆79Updated 3 years ago
- Code for the paper "Modelling Latent Translations for Cross-Lingual Transfer"☆17Updated 2 years ago
- ☆21Updated 3 years ago
- ☆44Updated 2 years ago
- ☆25Updated 2 years ago
- Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding☆18Updated last year
- The implementation of "Neural Machine Translation without Embeddings", NAACL 2021☆33Updated 3 years ago
- ☆34Updated 4 months ago
- ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation☆24Updated 3 years ago
- ☆17Updated 2 years ago
- ☆42Updated 4 years ago
- lanmt ebm☆11Updated 4 years ago
- PyTorch implementation of A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text (EMNLP 2019)☆46Updated 4 years ago
- Analyzing Uncertainty in Neural Machine Translation☆33Updated 3 years ago
- Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"☆23Updated 3 years ago
- Official code for the ICLR 2020 paper 'ARE PPE-TRAINED LANGUAGE MODELS AWARE OF PHRASES? SIMPLE BUT STRONG BASELINES FOR GRAMMAR INDCUTIO…☆30Updated last year
- ☆21Updated 3 years ago
- The Return of Lexical Dependencies: Neural Lexicalized PCFGs (TACL)☆33Updated 2 years ago
- ☆41Updated 3 years ago
- ☆12Updated 2 years ago
- This is a repository with the code for the EMNLP 2020 paper "Information-Theoretic Probing with Minimum Description Length"☆68Updated last month
- ☆25Updated this week
- Pytorch Seq2Seq framework☆26Updated 2 months ago
- ☆47Updated last year
- Non-Monotonic Sequential Text Generation (ICML 2019)☆73Updated 5 years ago
- ☆23Updated 7 months ago
- ☆12Updated last year
- Japanese--Russian--English News Commentary Parallel Data☆18Updated 5 years ago
- Small utility to monitor fairseq training in tensorboard☆21Updated 5 years ago
- Hard-Coded Gaussian Attention for Neural Machine Translation☆36Updated last year