Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation.
Fei HuangPei KeMinlie HuangPublished in: Trans. Assoc. Comput. Linguistics (2023)
Keyphrases
- autoregressive
- text generation
- high quality
- directed acyclic
- non stationary
- moving average
- gaussian markov random field
- random fields
- natural language generation
- random field models
- autoregressive model
- sar images
- suffix tree
- training set
- multi dimensional
- graphical models
- nearest neighbor
- pairwise
- edge preserving
- natural language
- autoregressive moving average
- bayesian networks
- machine learning