Alibaba and Microsoft make artificial intelligence programs reader gooder than humans on a Stanford University reading comprehension test.
Alibaba $BABA and Microsoft $MSFT make artificial intelligence programs reader gooder than humans on a Stanford University reading comprehension test.
Alibaba’s model scored 82.44 on the SQuAD test, beating the 82.304 by the human participants. Microsoft’s AI software also beat the human score, with a result of 82.650 a day later. This is the first time a machine has out-done a real person in such a test.
What is SQuAD?
Stanford Question Answering Dataset (SQuAD) is a new reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage. With 100,000+ question-answer pairs on 500+ articles, SQuAD is significantly larger than previous reading comprehension datasets.
“We believe the underlying technology can be gradually applied to numerous applications such as customer service, museum tutorials, and online response to inquiries from patients, freeing up human efforts in an unprecedented way”
Si Luo, a chief scientist of natural language processing at Alibaba’s research arm
The Group of 20 Economies (G20) financial regulator, the Financial Stability Board (FSB) warned about replacing humans with artificial Intelligence (AI) and Machine Learning. From self-driving cars and autonomous rig fleets to farming with AI replacing human workers.