You’re investing in a process that needs to evolve our way of working. “Organizations should not play chicken with the future,” Cruce says.“Invest in engineering content now before competitors’ robots steal customer mindshare.Chatbots are “computer programs which conduct conversation through auditory or textual methods”.Apple’s Siri, Microsoft’s Cortana, Google Assistant, and Amazon’s Alexa are four of the most popular conversational agents today.Some 60.5 million Americans now use a virtual assistant of some kind at least once a month.According to Gartner, chatbots will power 85% of all customer-service interactions by the year 2020.Question-and-answer (Q&A) content is everywhere in our organizations.It’s in customer documentation, in frequently asked questions (FAQs), in knowledge bases, in online help—and now, increasingly, in chatbot interfaces.
For all the progress we have made in the field, we too often get chatbot experiences like this.
It only makes sense to set up a single repository for all Q&A content, following the principles of the unified content strategy: write it once, use it where needed.
It’s counterproductive—and quickly becomes expensive and messy—when companies create a whole new repository of Q&A content for bots. Companies take an expedient approach rather than an intelligent approach.
Chatbots have been around for a decent amount of time (Siri released in 2011), but only recently has deep learning been the go-to approach to the task of creating realistic and effective chatbot interaction.
In this post, we’ll be looking at how we can use a deep learning model to train a chatbot on my past social media conversations in hope of getting the chatbot to respond to messages the way that I would.
In this post, we’ll be looking more at chatbots that operate solely on the textual front.