The RVL-CDIP benchmark is widely used for measuring performance on the t...
Document denoising and binarization are fundamental problems in the docu...
The ability of a document classifier to handle inputs that are drawn fro...
This paper introduces Augraphy, a Python package geared toward realistic...
Interest in dialog systems has grown substantially in the past decade. B...
Dialog systems must be capable of incorporating new skills via updates o...
To be robust enough for widespread adoption, document analysis systems
i...
Open Information Extraction (OIE) systems seek to compress the factual
p...
Task-oriented dialog systems need to know when a query falls outside the...
In a corpus of data, outliers are either errors: mistakes in the data th...