Image classification is one of AI's most common tasks, where a system is required to recognize an object from a given image. Yet real life requires us to recognize not a single standalone object but ...

Generally, a document in the real world (especially in the news domain) contains multiple concepts, so multi-label text classification is a very important technology for automatic metadata ...

In a paper, Amazon researchers describe X-Transformer, a machine learning model that tackles the problem of 'extreme' multi-label text classification.