Natural Language, But Artificially!

Natural Language, But Artificially!

GPT-3 turns customer feedback into actionable insights with human-like suggestions

Imagine a natural language program (NLP), used by a shopping mall being queried about what’s frustrating customers with the checkout experience, responding; “Customers are frustrated with the checkout flow because it takes too long to load. They also want a way to edit their address in checkout and save multiple payment methods.” There is no way to distinguish this computer-generated response from a human answer. This has been made possible by using OpenAI’s Generative Pre-trained Transformer 3 (GPT-3) an autoregressive language model that uses deep learning to produce human-like text.

A model language

It is a generative model which means that it can generate a long sequence of words that is coherent as an output. This state-of-the-art language model can respond to almost any question passed on to it and that too in a more humane way. Given any text prompt like a phrase or a sentence, GPT-3 returns a text completion in natural language. Developers can “program” GPT-3 by showing it just a few examples or “prompts.”

Turning customer feedback into actionable insights quickly has always been a challenge for organization. Viable, a start-up that makes customer feedback actionable by automating the process of structuring and labelling customer response, is one of the first companies to apply GPT-3 to get useful answers in human language. GPT-3’s ability to identify themes from natural language and generate summaries allows Viable to give product, customer experience, and marketing teams at companies across industries a better understanding of their customers’ wants and needs.

The best-known AI text-generator is OpenAI’s GPT-3, which the company recently announced is now being used in more than 300 different apps, by “tens of thousands” of developers, and producing 4.5 billion words per day. That’s a lot of robot verbiage. This may be a random milestone for OpenAI to celebrate, but it’s also a useful indicator of the growing scale, impact, and commercial potential of AI text generation.

Non-profit to profitability

OpenAI started life as a non-profit, but for the last few years, it has been trying to make money with GPT-3 as its first saleable product. The company has an exclusivity deal with Microsoft which gives the tech giant unique access to the program’s underlying code, but any firm can apply for access to GPT-3’s general API and build services on top of it. Viable is using GPT-3 to analyse customer feedback, identifying “themes, emotions, and sentiment from surveys, help desk tickets, live chat logs, reviews, and more.”

Another start-up Fable Studio is using the program to create dialogue for VR experiences. Fable Studio builds next-generation AI authoring tools to create interactive characters who can live, learn, and make decisions with users.

The roadblocks

A major worry about the rise of text-generating systems relates to issues of output quality. Like many algorithms, text generators have the capacity to absorb and amplify harmful biases. They’re also often astoundingly dumb. In tests of a medical chatbot built using GPT-3, the model responded to a “suicidal” patient by encouraging them to kill themselves. These problems aren’t insurmountable, but they’re certainly worth flagging in a world where algorithms are already creating mistaken arrests, unfair school grades, and biased medical bills.

© 2023 Praxis. All rights reserved. | Privacy Policy
   Contact Us
Praxis Tech School
PGP in Data Science