How bots are becoming more human: Natural Language Progression

Paving the way for fluid communication

I think we all know what happened with the ill-fated Tay the Chatbot experiment spearheaded by Microsoft. In retrospect, Tay was a dressed up mechanical parrot that lent itself to processing and repeating the information it was fed. It literally only took a few minutes before Tay turned into a foul-mouthed storm trooper, issues commands and dogma that were as much a surprise to the bot’s programmers as it was to the online community following Tay’s progress.

The playing field for linguistic software isn’t singular. Microsoft isn’t the only athlete coming out of the block, only the most well-known in the public’s eye.

Arria NLG to name one, offers a sophisticated software tool that combines cutting-edge techniques in data analytics and computational linguistics. These capabilities allow the engine to convert large and diverse datasets into meaningful natural language narratives, helping solve the problems of dealing with Big Data.

In short, Arria has made the process of converting data into narrative easy. We have built an AI that does what your human, natural intelligence does.

The dawn of natural language

Natural Language Generation is all about taking data and turning it into written or spoken language. This is indisputably the best way to provide actionable analytics. It’s how we as a species have communicated information and calls-to-action for tens of thousands of years. It’s a finely honed device that evolves as we evolve, and it marks us out from other species. It’s the best means by which we answer the requests “Tell me what I need to know” and “Tell me what I should do”.

Matt Gould, CSO & Co-Founder of Arria NLG feels the resulting problem with Tay could have been prevented with different technology.

“Right now we’re still playing question and answer with chatbots. But there’s still another level until the Internet can communicate with you naturally, until it can come back with a more general inference about the intent behind your question, and NLG is the solution that embodies the required expertise. To understand, conversely, is to be able to infer something from information received– analyzing and extracting insights from diverse data sets.”

Giving the internet a voice

Gould sees Natural Language Progression as a logical step in the progression of the bot marketplace. Comments Gould,

“The issue with today’s bots is their very limited areas of knowledge – these bots must fall back on search engines for anything outside of their narrow capabilities. The Internet is incredibly smart, but bots today are technologically equivalent to a two year-old just learning to speak for the first time. But bots can evolve with Natural Language Generation (NLG) technology.”

Gould feels that current NLG technologies can enable someone to have a free-flowing conversation with a bot, but none of the big tech companies have picked up on the intricacies involved. Not yet anyway.

NLG, explains Gould, “Combines state-of-the-art data science and analytics with cutting-edge computational linguistics techniques, delivering information that is hidden within data and conveying it through natural language.”

In other words, NLG gives the internet a voice without making it sound like a robot.

It provides an automated solution that can take diverse data sources, aggregate their information content, and deliver that content in a way that is immediately accessible. As a result of advancements in NLG, bots in the marketplace will become more sophisticated, useful, and friendly.

The IoT of bots

In the still evolving Internet of Things (IoT), will robots play a role? How do you best integrate AI with the IoD? As more and more of our everyday responsibilities are parceled out to smart technology, it’s not a stretch to see a robotic helper taking the lead: Doing our shopping, preparing dinner or even taking us to work in the morning.

To that end, Gould feels that all of the data gathered by every sensor in the world isn’t worth much if there’s a way of making use of it. Explains Gould,

“The real value that the Internet of Things brings is at the intersection of gathering data and leveraging it. We need to analyze that data, often in real time, if we are to extract its value, so we need an infrastructure for IoT data analysis.

…Bots might play a role in this infrastructure if their UX appeals to users and it can become a more effective way to interact than through a traditional user interface.”

The bottom line: No matter how sophisticated the analysis is of all that data, effective communication is the next major problem to be solved. The Internet of Things needs a voice. NLG can enable bots to provide an automated solution that can take those diverse data sources, aggregate their information content, and deliver that content in a way that is immediately accessible and makes sense.

#NaturalLanguageProgression