State-of-the-art NLP models can adopt shallow heuristics that limit thei...
In this paper, we explore how QuestEval, which is a Text-vs-Text metric,...
Data-to-Text Generation (DTG) is a subfield of Natural Language Generati...
In language generation models conditioned by structured data, the classi...
Despite efforts to distinguish three different evaluation setups (Bekoul...
Transcribing structured data into natural language descriptions has emer...