Follow Us:
Saturday, June 19, 2021

Microsoft AI technology tops Stanford comprehension test; can interpret documents like humans

Microsoft's artificial intelligence has shown the capability to interpret details as accurately as humans, and outscored Alibaba's AI system in Stanford's comprehension test.

By: IANS | San Francisco |
January 16, 2018 4:23:48 pm
Microsoft AI system, artificial intelligence, Stanford University comprehension, machine learning, Stanford Question Answering Dataset, Wikipedia articles, language processing, human performance The scores submitted by Microsoft and Alibaba’s AI systems indicate how machine learning algorithms can help interpret reports like humans, and present important details in pressure situations. (File Photo)

Microsoft researchers have created a technology that uses Artificial Intelligence (AI) to read a document and answer questions about it about as well as a human. “It’s a major milestone in the push to have search engines such as Bing and intelligent assistants such as Cortana interact with people and provide information in more natural ways, much like people communicate with each other,” Allison Linn, senior writer at Microsoft, wrote in a blog post on Tuesday.

The team at Microsoft Research Asia reached the human parity milestone using the ‘Stanford Question Answering Dataset’, known among researchers as ‘SQuAD’. It’s a machine reading comprehension dataset that is made up of questions about a set of Wikipedia articles. According to the SQuAD leaderboard, Microsoft submitted a model that reached the score of 82.650 on the exact match portion. The human performance on the same set of questions and answers is 82.304.

On January 5, researchers with the Chinese e-commerce company Alibaba submitted a score of 82.440, also about the same as a human. “The two companies are currently tied for first place on the SQuAD ‘leaderboard’ which lists the results of research organisations’ efforts,” the post read. With machine reading comprehension, researchers say computers also would be able to quickly parse through information found in books and documents and provide people with the information they need most in an easily understandable way.

That would let drivers more easily find the answer they need in a dense car manual, saving time and effort in tense or difficult situations. “These tools also could let doctors, lawyers and other experts more quickly get through the drudgery of things like reading through large documents for specific medical findings or rarified legal precedent,” Linn said. According to Ming Zhou, Assistant Managing Firector of Microsoft Research Asia, the “SQuAD” dataset results are an important milestone, but overall, people are still much better than machines at comprehending the complexity and nuance of language.

“Natural language processing is still an area with lots of challenges that we all need to keep investing in and pushing forward,” Zhou said. “This milestone is just a start.”

📣 The Indian Express is now on Telegram. Click here to join our channel (@indianexpress) and stay updated with the latest headlines

For all the latest Technology News, download Indian Express App.

  • The Indian Express website has been rated GREEN for its credibility and trustworthiness by Newsguard, a global service that rates news sources for their journalistic standards.