AI’s Next Generation Natural Language Understanding API
Join the private beta waitlist
Join the waitlist for our private beta and updates in our Slack channel. No spam.
* All fields are required.
Language Based AI
Pat Inc. is teaching language to machines. We deliver meaning-as-a-service: connecting natural language with structured information that creates meaning and understanding. Pat Inc. is building the world’s most powerful natural language service for developers to build intelligent agents and applications that you can talk to or text.
Linguistics not Statistics
The difference with Natural Language Understanding (NLU) is not in how it translates words or guesses the intent of a question. It understands the true meaning of sentences and conversations. Pat Inc. takes a linguistic approach to NLU, not statistical or machine learning based. After all, humans don’t learn language reading thousands of books and memorising colocation patterns and probabilities.
Training Data Not Required
Rather than training data or annotated corpora, Pat builds knowledge on language just like a human by progressively learning the way words are combined, regarding real objects, people, processes, and events in context. Pat is not trying to learn patterns about language meaning from big data, an approach that is still struggling to beat the language capabilities of a 3-year-old.
Pat Inc.’s approach to NLU is language independent and delivers one solution across all languages. The meaning of a sentence or conversation is mapped regardless of the language. In fact, multiple languages can even be mixed up within a single sentence or conversation and still connect to meaning.
"The amazing John Ball of @PatisNLU has been a trailblazer for decades. His work forms the path of the next frontier of the #VoiceFirst revolution. There’s a fork in the road ahead for #VoiceFirst technology:
- Brute force machine learning of words
- Words in sentences surmised to meaning and intent
— Brian Roemmele
Recognized global authority on voice AI, President of Multiplex,
Scientist, Researcher, Analyst, Highly regarded futurist and expert contributor
— Dr. Hossein Eslambolchi
Open Lab Technical Advisor at Facebook, Chairman & CEO at 2020 Venture Partners,
Top 10 Influential Leader of the 21st Century, 1000+ patents BS, MS, Ph.D, UCSD
— Professor Robert D. Van Valin, Jr
Global linguist expert, University of Dusseldorf, University of Buffalo and State University of New York,
Author of 7+ books and 100+ publications
— Chris Lonsdale
Global technology advisor, linguist and educator,
TEDx speaker with 13+M views, Author of 2+ books
Pat Inc. bridges five decades of functional linguistic studies in Role and Reference Grammar with three decades of cognitive science studies in Patom Theory. This miraculous combination would shape the future of the next generation of humanized machines that can exactly understand the human languages. Pat’s meaning-matcher engine makes this dream a tangible reality.
Natural Language for Developers
Pat Inc. offers next generation NLU for developers to build language-based applications and devices for users to engage, talk and text. Our vision is to humanize conversations with machines. Pat doesn’t need corpora to train on a new domain. We’re teaching machines language, not data. In functional linguistics the words and phrases connect to meaning or as we say, Form follows Meaning™.
Search engines put the world’s wealth of information at our fingertips, but imagine the difference if you could search with natural language? Google knows firsthand the frustration todays state-of-the-art causes users, who often need to try a number of different search results to find the answer they are looking for.
- Human-Machine Conversation
Customer Service intelligent assistant
Key decisions in the financial markets are increasingly moving away from human oversight and control. Algorithmic trading is becoming more standard, a form of financial investing that is entirely controlled by technology. But, many of these financial decisions are impacted by news and by journalism, which is still presented predominantly in English.
- Sentiment analysis
- Text analysis
IoT and Robotics
Today we have started talking to our smart homes and home robots. How much better will this be with natural language that understands when we make corrections to our spoken words and its response more closely mimics a human? When ambiguity is handled or clarified. We are only at the beginning of the social robot and home automation revolution.
- Home Automation
- Conversational User Interface
How does it work?
Subscribe for updates
Don’t worry, we’ll only send you the best stuff – no spam.