Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation
–Neural Information Processing Systems
Non-autoregressive translation (NA T) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions.
Neural Information Processing Systems
Aug-22-2025, 00:01:42 GMT
- Country:
- Asia > China
- Hong Kong (0.04)
- Europe
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Czechia > Prague (0.04)
- Germany > Berlin (0.04)
- Italy > Tuscany
- Florence (0.04)
- United Kingdom > Scotland
- City of Edinburgh > Edinburgh (0.04)
- Belgium > Brussels-Capital Region
- North America
- Canada > British Columbia
- Vancouver (0.04)
- Dominican Republic (0.04)
- United States
- California > San Diego County
- San Diego (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Maryland > Baltimore (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.04)
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- Texas > Travis County
- Austin (0.04)
- Washington > King County
- Seattle (0.04)
- California > San Diego County
- Canada > British Columbia
- Asia > China
- Genre:
- Research Report (0.46)
- Technology: