Transformer-XL

Large transformer networks work wonders with natural language, but they require enormous amounts of computation. New research slashes processor cycles without compromising performance.

Watson set a high bar for language understanding in 2011, when it famously whipped human competitors in the televised trivia game show Jeopardy! IBM’s special-purpose AI required around $1 billion. Research suggests that today’s best language models can accomplish similar tasks right off the shelf.