Sreeparna Mukherjee

CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals

We propose a framework to modularize the training of neural language models that use diverse forms of context by eliminating the need to jointly train context and within-sentence encoders. Our approach, contextual universal embeddings (CUE), trains LMs on one type of contextual data and adapts to no…