P$^3$LM: Probabilistically Permuted Prophet Language Modeling for Generative Pre-Training
Bao, Junwei, Wang, Yifan, Ying, Jiangyong, Gong, Yeyun, Zhao, Jing, Wu, Youzheng, He, Xiaodong
–arXiv.org Artificial Intelligence
Conventional autoregressive left-to-right (L2R) sequence generation faces two issues during decoding: limited to unidirectional target sequence modeling, and constrained on strong local dependencies. To address the aforementioned problem, we propose P$^3$LM, a probabilistically permuted prophet language model, which strengthens the modeling of bidirectional information and long token dependencies for sequence generation. Specifically, P$^3$LM learns to generate tokens in permuted order upon an order-aware transformer decoder, as well as to generate the corresponding future $N$ tokens with a multi-stream attention mechanism. Extensive experiments are conducted on the GLGE benchmark, which includes four datasets for summarization, two for question generation, one for conversational question answering, and one for dialog response generation, where P$^3$LM achieves state-of-the-art results compared with strong publicly available generative pre-training methods.
arXiv.org Artificial Intelligence
Oct-21-2022
- Country:
- Oceania > Australia
- North America
- United States
- Texas (0.04)
- Michigan (0.04)
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- San Francisco County > San Francisco (0.14)
- Los Angeles County > Long Beach (0.14)
- San Diego County > San Diego (0.04)
- Puerto Rico > San Juan
- San Juan (0.04)
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.14)
- United States
- Europe
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Portugal > Lisbon
- Lisbon (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Spain > Catalonia
- Asia > China
- Hong Kong (0.04)
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- Genre:
- Research Report (1.00)
- Technology: