This year the International Conference on Natural Language Generation (I...
This case study investigates the extent to which a language model (GPT-2...
We observe a severe under-reporting of the different kinds of errors tha...
Machine learning approaches applied to NLP are often evaluated by summar...
Preregistration refers to the practice of specifying what you are going ...
We introduce GEM, a living benchmark for natural language Generation (NL...
Automatic image description systems are commonly trained and evaluated u...
Traditionally, most data-to-text applications have been designed using a...
Automatic image description systems are commonly trained and evaluated o...
In recent years we have seen rapid and significant progress in automatic...
We provide a qualitative analysis of the descriptions containing negatio...
An untested assumption behind the crowdsourced descriptions of the image...
This paper presents a pattern-based method that can be used to infer
adj...