Natural language processing (NLP) is among the fastest growing applications of artificial intelligence (AI). It’s also one of the most difficult to build. NLP powers a growing number of tools, such as chatbots, virtual assistants like Amazon’s Alexa, and even the spell check for the communication apps we use to send text messages from our devices.

The recent failure of IBM’s Project Debater in its contest against global debate champion Harish Natarajan offers the latest in a series of lessons learned about the deployment of natural language processing (NLP) technology in the real world. Project Debater is one of numerous attempts in a decades-old quest to use machines to automate the analysis of language to gather insights and make decisions.

“Hey Siri,” I said. “Call Nancy. Mobile.” Siri replied, “Calling Lindsay. Mobile.” It began to ring. I hadn’t worked with Lindsay in six years. I lunged for my phone and touched the red button just in time to avoid what would no doubt have been an awkward, out-of-the-blue conversation with her. Then, I contemplated the complexities of NLP development.