Evaluating Information Coverage
Matt, Ondřej, and Verena discuss the challenges of automatically evaluating informativeness in meaning representation. They delve into the complexities of content selection and the impact of data quality on evaluation metrics, highlighting the need for creative solutions in natural language processing.In this clip
From this podcast

NLP Highlights
108 - Data-To-Text Generation, with Verena Rieser and Ondřej Dušek
Related Questions