Meta AI’s LegoNN Builds Decoder Modules That Are Reusable Across Diverse Language Tasks Without Fine-Tuning
In the new paper LegoNN: Building Modular Encoder-Decoder Models, Meta AI researchers propose LegoNN, a procedure for building encoder-decoder architectures with decoder modules that can be shared ...
Source: syncedreview.com
In the new paper LegoNN: Building Modular Encoder-Decoder Models, Meta AI researchers propose LegoNN, a procedure for building encoder-decoder architectures with decoder modules that can be shared across different tasks without finetuning or significant performance reductions.