Chinese tech giant Baidu, which is China’s closest equivalent to Google, just dethroned both Microsoft and Google in an ongoing competition in AI earlier this month. The competition was the General Language Understanding Evaluation, or GLUE for short.
GLUE is a widely accepted benchmark for how well an AI system understands human language. It consists of nine different tests for things like picking out the names of people and organizations in a sentence and figuring out what a pronoun like “it” refers to when there are multiple potential antecedents. A language model that scores highly on GLUE, therefore, can handle diverse reading comprehension tasks. Out of a full score of 100, the average person scores around 87 points.
Baidu has now become the first team to surpass 90 points through the use of their model, ERNIE (which stands for “Enhanced Representation through kNowledge IntEgration”).
How does the model work? Find out over at Technology Review.
(Image Credit: geralt/ Pixabay)