NVIDIA Sees Major Breakthroughs In Language Understanding For Real-Time Conversational AI

By Amit Chowdhry ● August 13, 2019
  • Today NVIDIA announced breakthroughs in language understanding to allow businesses to engage more naturally with customers using real-time conversational AI

Today NVIDIA announced breakthroughs in language understanding that allow businesses to engage more naturally with customers using real-time conversational AI. NVIDIA’s AI platform was the first to train one of the most advanced AI language models (BERT) in less than an hour and complete AI inference in just over 2 milliseconds.

And this groundbreaking level of performance makes it possible for developers to use state-of-the-art language understanding for large-scale applications they can make available to hundreds of millions of consumers worldwide. The early adopters of NVIDIA’s performance advances include Microsoft and some of the world’s most innovative startups, which are utilizing NVIDIA’s platform to develop highly intuitive and immediately responsive language-based services for their customers.

The limited conversational AI services have existed for several years. However, it has been difficult for chatbots, intelligent personal assistants, and search engines to operate with human-level comprehension due to the inability to deploy extremely large AI models in real-time until this point. NVIDIA addressed this problem by adding key optimizations to its AI platform thus achieving speed records in AI training and inference and building the largest language model of its kind to date.


“Large language models are revolutionizing AI for natural language,” said NVIDIA VP of Applied Deep Learning Research Bryan Catanzaro. “They are helping us solve exceptionally difficult language problems, bringing us closer to the goal of truly conversational AI. NVIDIA’s groundbreaking work accelerating these models allows organizations to create new, state-of-the-art services that can assist and delight their customers in ways never before imagined.”

The AI services powered by natural language understanding are expected to grow exponentially in the coming years. And digital voice assistants alone are anticipated to climb from 2.5 billion to 8 billion within the next four years, according to Juniper Research. Plus Gartner is predicting by 2021 that 15% of all customer service interactions will be completely handled by AI, an increase of 400% from 2017.

NVIDIA had fine-tuned its AI platform with key optimizations that resulted in three new natural language understanding performance records including:

1.) Fastest training: Running the large version of one of the world’s most advanced AI language models — Bidirectional Encoder Representations from Transformers (BERT) — an NVIDIA DGX SuperPOD using 92 NVIDIA DGX-2H systems running 1,472 NVIDIA V100 GPUs slashed the typical training time for BERT-Large from several days to just 53 minutes. And additionally, NVIDIA trained BERT-Large on just one NVIDIA DGX-2 system in 2.8 days – demonstrating NVIDIA GPUs’ scalability for conversational AI.

2.) Fastest inference: Using NVIDIA T4 GPUs running NVIDIA TensorRT, NVIDIA performed inference on the BERT-Base SQuAD dataset in only 2.2 milliseconds – which is well under the 10-millisecond processing threshold for many real-time applications and a sharp improvement from over 40 milliseconds measured with highly optimized CPU code and

3.) Largest model: With a focus on developers’ ever-increasing need for larger models, NVIDIA Research had built and trained the world’s largest language model based on Transformers, the technology building block used for BERT and a number of other natural language AI models. And NVIDIA’s custom model — with 8.3 billion parameters — is 24 times the size of BERT-Large.

There are hundreds of developers worldwide that are already using NVIDIA’s AI platform to advance their own language understanding research and create new services. For example, Microsoft Bing is using the power of its Azure AI platform and NVIDIA technology to run BERT and drive more accurate search results.

“Microsoft Bing relies on the most advanced AI models and computing platform to deliver the best global search experience possible for our customers,” added Microsoft Bing group program manager Rangan Majumder. “In close collaboration with NVIDIA, Bing further optimized the inferencing of the popular natural language model BERT using NVIDIA GPUs, part of Azure AI infrastructure, which led to the largest improvement in ranking search quality Bing deployed in the last year. We achieved two times the latency reduction and five times throughput improvement during inference using Azure NVIDIA GPUs compared with a CPU-based platform, enabling Bing to offer a more relevant, cost-effective, real-time search experience for all our customers globally.”

And several startups in NVIDIA’s Inception program including Clinc, Passage AI and Recordsure are also using NVIDIA’s AI platform to build cutting-edge conversational AI services for banks, car manufacturers, retailers, healthcare providers, travel and hospitality companies, etc.

Clinc specifically made NVIDIA GPU-enabled conversational AI solutions accessible to over 30 million people globally through a customer roster that includes leading car manufacturers, healthcare organizations, and some of the world’s largest financial institutions like Barclays, USAA, and Isbank.

“Clinc’s leading AI platform understands complex questions and transforms them into powerful, actionable insights for the world’s leading brands,” explained Clinc CEO Jason Mars. “The breakthrough performance that NVIDIA’s AI platform provides has allowed us to push the boundaries of conversational AI and deliver revolutionary services that help our customers use technology to engage with their customers in powerful, more meaningful ways.”