When it was released by Google just a few years ago, a deep-learning model called BERT demonstrated a major step forward in natural language processing (NLP). BERT's core structure, based on a type of neural network known as a Transformer, has become the underpinning for a range of NLP applications, from completing search queries and user-written sentences to language translation.
The models even score well on benchmarks intended to test understanding at a high school level, such as Large-scale ReAding Comprehension (RACE) developed at Carnegie Mellon University. In doing so, they have become marketing tools in the artificial intelligence (AI) gold rush. At Nvidia's annual technology conference, president and CEO Jen-Hsun Huang used RACE to claim high performance for his company's implementation of BERT.
No entries found
Log in to Read the Full Article
Sign in using your ACM Web Account username and password to access premium content if you are an ACM member, Communications subscriber or Digital Library subscriber.
Please select one of the options below for access to premium content and features.
Create a Web Account
If you are already an ACM member, Communications subscriber, or Digital Library subscriber, please set up a web account to access premium content on this site.
Join the ACM
Become a member to take full advantage of ACM's outstanding computing information resources, networking opportunities, and other benefits.
Subscribe to Communications of the ACM Magazine
Get full access to 50+ years of CACM content and receive the print version of the magazine monthly.
Purchase the Article
Non-members can purchase this article or a copy of the magazine in which it appears.