bagequan

tencent-transformer-with-disagreement

Multi-Head Attention with Disagreement Regularization

Levenshtein-Transformer

MS-BCS-DDQ

Budgeted Policy Learning for Task-Oriented Dialogue Systems

capsule

CMLM

Constant-Time Machine Translation with Conditional Masked Language Models

egit

ELMo-chinese

Deep contextualized word representations 中文 汉语

LATEXT-GAN

Latent Code and Text-based Generative Adversarial Networks for Soft-text Generation

multi-task

tencent_Modeling-Localness-for-Self-Attention-Networks