Natural language processing is a type of artificial intelligence in which computational and mathematical methods are used to analyze the human language. NPL’s goal for end users is to facilitate interactions with computers using conversational language. Subtopics in this genre include natural language understanding, which is about understanding the inputs created by humans, and natural language generation, which focuses on generating natural language narratives.

The most popular approaches to NLP use machine learning, said Adrian Bowles, vice president of Research and lead analyst at Aragon Research. “At the most advanced levels in the research labs today, we see applications or systems like Google Duplex, which can act as an agent to perform tasks like scheduling haircuts over the phone by engaging with humans, or IBM’s Debater, which can detect patterns of logical arguments in free form text and construct a coherent and novel narrative position statement.”

Related Article: What Is Natural Language Processing? And How Can it Facilitate Content Marketing

Why the Time Is Ripe for NLP

The earliest attempts to analyze human language using computational methods started 50 years ago, said Riversand Technologies’ Data Science and Analytics Program Manager Vivek Anand but it has only been recently that these methods have achieved commercial and technical success. Several factors have led to the emergence of NLP, which range from the miniaturization of electronics — precluding the use of physical or onscreen keyboards — to the proliferation of digital data available for processing.

“These developments, coupled with the exponential increase in the computational power of computers and the ability to handle enormous volume of data has resulted in the development of highly sophisticated mathematical models — such as deep learning neural networks — that enable computers to process conversational language,” Anand said.

Related Article: What Is a Neural Network and How Are Businesses Using Them?

How NLP Is Used Today and in the Future

Anyone who asks Siri or Alexa a question is using NLP, Trill A.I. co-founder and CEO Akash Ganapathi said. Likewise customer service chatbots. “Some of the more ubiquitous applications of NLP today include virtual assistants, customer service, sentiment analysis and translation,” he said.

Learning Opportunities

But as the technology continues to develop and evolve, future applications will be more exciting and useful, Ganapathi continued. For example, virtual assistants will be able to answer more complicated questions taking into account the implications along with the literal meaning. (Q: What’s the weather like? A: Warm, you’ll be most comfortable in shorts and a t-shirt). “Businesses will be able to provide more professional customer service, take calls instantly and escalate problems that actually require people,” Ganapathi said. 

Randy Frei, vice president of Engineering at Mist Systems, gave the example of using NLP to ask "what is wrong with my network?" Today NLP can be trained to provide a list of errors, he said, but in the future the technology will be able to understand the user’s real intent — namely that he wants his network fixed so he can access it. “These advances in natural language processing will allow us to shift focus from the questions to the results — from better understanding of the user’s input to providing more complex answers and actions that correspond to the user’s true intent,” Frei said.

Related Article: A Good Chatbot Is Hard to Find

NLP Will Infer a Wider Range of Emotions

This is because as NLP technology improves, computers will be able to not only process but also understand human language in a holistic sense, said Riversand Technologies’ Anand. Until now, NLP has been restricted to infer a limited range of emotions such as joy or anger, he explained. Eventually NLP will be able to understand more complex elements of language such as humor, sarcasm, satire, irony and cynicism.

Also coming in the future: NLP will be used with other technologies such as facial and gesture recognition, which will be of great benefit to businesses, Anand continued. For example, “automatic summarization of large quantities of documents such as reports, memos and emails using NLP would be of tremendous value to business leaders in quickly getting a pulse about their industry and competitors,” he said. NLP coupled with business intelligence, “would enable extraction of actionable insights in language form, thereby making businesses agile and efficient.”