Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation.
Fei HuangPei KeMinlie HuangPublished in: CoRR (2023)
Keyphrases
- autoregressive
- text generation
- high quality
- directed acyclic
- non stationary
- moving average
- gaussian markov random field
- natural language generation
- training set
- random fields
- graphical models
- random field models
- bayesian networks
- graph structure
- autoregressive model
- image quality
- data structure
- sar images
- information retrieval
- fault diagnosis
- suffix tree
- autoregressive moving average
- artificial intelligence