Search

Philipp Koehn

X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
Streaming Sequence Transduction through Dynamic Compression
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
Efficiently Harnessing Parameter Importance for Better Training
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains
Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
Cross-Lingual BERT Contextual Embedding Space Mapping with Isotropic and Isometric Conditions