SOURCE-LINKED INTELLIGENCE

DEep COgnition Learning for LAnguage GEneration

CORDIS · observation · Publication date unknown

DEep COgnition Learning for LAnguage GEneration In recent years, transformer-based deep learning models such as BERT or GPT-3 have led to impressive results in many natural language processing (NLP) tasks, exhibiting transfer and few-shot learning capabilities. However, despite faring well in benchmarks, current deep learning models for NLP often fail badly in the wild: they are bad at out-of-domain generalization, they do not exploit contextual information, they are poorly calibrated, and their memory is not traceable. These limitations stem from their monolithic architectures, which are good for perception, but unsuitable for tasks requiring higher-level cognition. In this project, I attack these fundamental problems by bringing together tools and ideas from machine learning, sparse modeling, information theory, and cognitive science, in an interdisciplinary approach. First, I will use uncertainty and quality estimates for utility-guided controlled generation, com

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

1999595

unit

EUR