By Tim Joyce, CIO at WDS, A Xerox Company
Before digital self-care tools can interact with your customers, they must understand what’s being said. By the age of six, most children can understand not only spoken language, but also its subtle complexities like ambiguity, novel words, and non-literal expressions. While children are able to understand the nuances of spoken language, technology’s ability to detect the same linguistic intricacies, is largely in its infancy.
What Tools do Machines Need to Understand Humans?
Computers work from a logical standpoint, taking everything they come across literally. Thus, while it’s easy for us humans to understand our freeform use of language, it’s surprisingly difficult for machines. With over 80% of information represented in the form of language it is an important challenge that needs to be overcome.
Natural language processing, an arm of artificial intelligence, improves technology’s ability to understand how humans use language. It is the first step toward a future where people may naturally interact with computers using normal, familiar expressions. It requires systems to convert the words and phrases that people use into formal semantic representations in order to extract meaning that can be understood and acted upon.
Why is Natural Language Processing so Difficult to Achieve?
Natural language processing requires analysis of underlying linguistic structures and relationships, from grammatical rules to explicit concepts, implicit meanings to logic and discourse context. As individual words and sentences can have multiple meanings, researchers have found that a single concept can be expressed in many different ways. The ambiguity that can arise when interpreting a single sentence poses a significant challenge to machines.
When people come across such ambiguous use of language, we are able to infer meaning from the implicit context and draw from personal knowledge and understanding. Computers don’t benefit from the subtleties of human experience and learning, they don’t have our “common sense.”
To understand our world, computers require information to be what language is not, namely precise, unambiguous and highly structured. That is what natural language processing is all about.
Why Does Natural Language Processing Matter Today?
As customers, and thus brands, move more and more of their interactions to digital channels, it is increasingly important for brands to understand what’s being said in order to interact with the customers via this new media.
User-generated content such as blogs, forums and micro-posts do not follow universal, unambiguous structures. They are difficult to analyze without the right understanding of the context of the situation, the culture in question, and even the very specific topic or people involved.
The Next Step in Customer Care
Scientists at Palo Alto Research Center (PARC) and the Xerox Research Center Europe (XRCE) have been leading the way in natural language processing developments for decades. Here, Will Radford, a researcher at XRCE, discusses the challenges and opportunities of automating natural dialogue in the customer care sphere.
Xerox natural language processing is able to understand complex, informal linguistic expressions, and combine them with machine learning to improve online conversations. This has many highly useful applications; ranging from fact checking to automated customer issue handling.
In customer care, this creates opportunities for customers to interact directly with virtual agents without having to change their communication patterns and preferences. What’s more, these digital customer care channels will be able to understand accurately and quickly what customers are saying.
Based on Xerox research, WDS Virtual Agent takes some important initial steps, with both natural language processing and machine learning technologies, to automate an accurate understanding of customer needs and expectations, and respond appropriately to meet them.
This article was first published on the WDS blog.
Subscribe to Simplify Work and receive email updates when we publish a new article.