Connect with us

Tech News

How bots are becoming more human: Natural Language Progression

Giving the internet a voice without making it sound like a robot. That’s the challenge of Arria NLG, a prime example of how natural language progression is making bots more human.

Published

on

nlg arria intelligence

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.

bar
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

Nearly three decades living and working all over the world as a radio and television broadcast journalist in the United States Air Force, Staff Writer, Gary Picariello is now retired from the military and is focused on his writing career.

Tech News

You’ve seen the job listings, but what exactly *is* UX writing?

(TECH NEWS) We seeing UX writer titles pop up and while UX writing is not technically new, there are new availabilities popping up.

Published

on

UX writing

The work of a UX writer is something you come across everyday. Whether you’re hailing an Uber or browsing Spotify for that one Drake song, your overall user experience is affected by the words you read at each touchpoint.

A UX writer facilitates a smooth interaction between user and product at each of these touch points through carefully chosen words.

Some of the most common touchpoints UX writers work on are interface copy, emails and notifications. It doesn’t sound like the most thrilling stuff, but imagine using your favorite apps without all the thoughtful confirmation messages we take for granted. Take Eat24’s food delivery app, instead of a boring loading visual, users get a witty message like “smoking salmon” or “slurping noodles.”

Eat24’s app has UX writing that works because it’s engaging.

Xfinity’s mobile app provides a pleasant user experience by being intuitive. Shows that are available on your phone are clearly labeled under “Available Out of Home.” I’m bummed that Law & Order: SVU isn’t available, but thanks to thoughtful UX writing at least I knew that sad fact ahead of time.

Regardless of where you find a UX writer’s work, there are three traits an effective UX writer must have. Excellent communication skills is a must. The ability to empathize with the user is on almost every job post.

But from my own experience working with UX teams, I’d argue for the ability to advocate as the most important skill.

UX writers may have a very specialized mission, but they typically work within a greater UX design team. In larger companies some UX writers even work with a smaller team of fellow writers. Decisions aren’t made in isolation. You can be the wittiest writer, with a design decision based on obsessive user research, but if you can’t advocate for those decisions then what’s the point?

I mentioned several soft skills, but that doesn’t mean aspiring UX writers can’t benefit from developing a few specific tech skills. While the field doesn’t require a background in web development, UX writers often collaborate with engineering teams. Learning some basic web development principles such as responsive design can help writers create a better user experience across all devices. In a world of rapid prototyping, I’d also suggest learning a few prototyping apps. Several are free to try and super intuitive.

Now that the UX in front of writer no longer intimidates you, go check out ADJ, The American Genius’ Facebook Group for Austin digital job seekers and employers. User-centric design isn’t going anywhere and with everyone getting into the automation game, you can expect even more opportunities in UX writing.

Continue Reading

Tech News

AI cameras could cut down traffic deaths, but there may be flaws

(TECH NEWS) Traffic accidents have plagued humanity since motor vehicles were created, can AI help cut down on text and drive incidents?

Published

on

AI camera

What if we told you Australian officials believe they have found a way to reduce driving deaths by almost 30% in just two years? It’s a pretty appealing concept. After all, Australia alone faces an average of over 3 deaths a day due to driving accidents. And Australia’s average death rate clocks in at just half of what we face in the United States.

There’s just one problem with Australia’s proposed solution: it’s basically Big Brother.

Basically, Australia plans to use AI cameras to catch people texting and driving. There are plenty of places that have outlawed texting and driving, but that rule is very hard to enforce – it basically means catching someone in the act. With AI cameras, hands free driving can be monitored and fined.

Australia has already started rolling out some of these systems in South Wales. Because this is a new initiative, first time offenses will be let off with a warning. The following offenses can add up quickly, though, with fines anywhere from $233 to $309 USD. After a six month trial period, this program is projected to expand significantly.

But there are real concerns with this project.

Surprisingly, privacy isn’t one of these worries. Sure, “AI cameras built to monitor individuals” sounds like a plot point from 1984, but it’s not quite as dire as it seems. First, many places already have traffic cameras in order to catch things like people running red lights. More importantly, though, is the fact these machines aren’t being trained to identify faces. Instead, the machine learning for the cameras will focus on aspects of distracted driving, like hands off the wheel.

The bigger concern is what will come from placing the burden of proof on drivers. Because machine learning isn’t perfect, it will be paired with humans who will review the tagged photographs in order to eliminate false positives. The problem is, humans aren’t perfect either. There’s bound to be false positives to fall through the cracks.

Some worry that the imperfect system will slow down the judicial system as more people go to court over traffic violations they believe are unfair. Others are concerned that some indicators for texting while driving (such as hands off the wheel) might not simply apply texting. What if, for instance, someone was passing a phone to the back seat? Changing the music? There are subtleties that might not be able to be captured in a photograph or identified by an AI.

No matter what you think of the system, however, only time can tell if the project will be effective.

Continue Reading

Tech News

News site seems run by robot Ron Burgundy with tourettes

(TECH NEWS) You can find a possible look into the future of bot generated content on TechZimo. Beware though, it is filled with errors.

Published

on

TechZimo bot writer

If you have had any nightmares about the singularity, aka robot apocalypse, let me put those fears to bed. In actuality the doomsday scenario will be much more clumsy and stupid looking than you ever thought robots could be.

As a Web Producer, I am entrenched in research – and today, I came across a site I hadn’t seen before – techzimo.com. After reading the first 2 sentences of an article about Uber, I began to think something felt a bit off about the writing.

Quotation marks were pressed right against the words before it, like”this”. Now the article didn’t include that many quotes, but what it did inhabit was a tangential synonym that didn’t quite contain.

If you felt your mind pause for a second while reading that last sentence, you’re not alone. You’ll notice some of the words almost work together, but not quite, and those kinds of mishmoshed sentences and punctuation faux pas are exactly what I was dealing with when reading the article.

Technically the quotes were around the right words, but the placement of the quotation marks in the rest of the sentence was all kinds of wrong. Also, some of the words used do technically equate to the concept the “writer” was looking to achieve, but given my experience, a real live human would use different words that are easier to understand…right?

After powering my way through the badly worded, weird misquoted article, I looked at who the author was. “Team TechZimo” wrote the piece, I immediately thought “Oh, well if there is a story no one wants to cover, maybe they throw a bot on the story and just let it go?”

Then I looked at how many articles “Team TechZimo” had written – 720 posts, but that’s not all, while writing to this point that number has reached 727. in the hour since I first looked at the site, 7 more articles were written, I thought “that has to be a bot.”

But that cant be…that’s an insane number of articles for a company to hand to a bot. So I looked at the home page to view all the articles, and I’ll bet you can guess what I found.

All were written by “Team TechZimo.”

That’s right. Every single article on this site was bot written.

My next question was “how long this had been going on?” So I investigated. The very first article was written on January 31st, 2020, and 39 articles were written the day they opened the site!

To recap and to further drive home my point, this entire site did not exist 1 month ago but now has 729 articles up. Every one of those articles are filled with errors, but maybe not egregious enough issues to ring an average reader’s alarm bells.

So naturally the next thing I wondered was why? Why create a site that improperly writes news stories that people may want to read? My first guess is ad space, every page has ads. A single person can get a writing bot for free (I will not link one!), pay for a domain, get that bot a writin, and profit from generic ads.

I realize that by writing this and linking to the TechZimo site, I am almost contributing to the validity of this issue, but honestly I am more worried about the people who do not scrutinize their news sources.

Lucky for you (and other fact-driven readers), it seems many of the articles are mostly filled with plain facts. The only problem was with punctuation and word choice.

So while you are out inquiring the internet, be sure to”keep your eye to the grindstone,” and beware of this or any other one-authored sites that within 1 month, has 730 articles and zero comments.

Continue Reading
Advertisement

Our Great Partners

The
American Genius
news neatly in your inbox

Subscribe to our mailing list for news sent straight to your email inbox.

Emerging Stories

Get The American Genius
neatly in your inbox

Subscribe to get business and tech updates, breaking stories, and more!