Marketers’ interest in chatbots is growing rapidly. Globally, 57% of firms that Forrester surveyed are already using chatbots or plan to begin doing so this year. However, marketers struggle to deliver value. My latest report, Chatbots Are Transforming Marketing, shows B2C marketing professionals how to use chatbots for marketing by focusing on the discover, explore, […]
You can structure these modules to flow in any way you like, ranging from free form to sequential. The Bot Framework SDK provides several libraries that allows you to construct any conversational flow your bot needs. For example, the prompts library allows you to ask users for input, the waterfall library allows you to define a sequence of question/answer pair, the dialog control library allows you to modularized your conversational flow logic, etc. All of these libraries are tied together through a dialogs object. Let's take a closer look at how modules are implemented as dialogs to design and manage conversation flows and see how that flow is similar to the traditional application flow.
Getting the remaining values (information that user would have provided to bot’s previous questions, bot’s previous action, results of the API call etc.,) is little bit tricky and here is where the dialogue manager component takes over. These feature values will need to be extracted from the training data that the user will define in the form of sample conversations between the user and the bot. These sample conversations should be prepared in such a fashion that they capture most of the possible conversational flows while pretending to be both an user and a bot.
“Utility gets something done following a prompt. At a higher level the more entertainment-related chatbots are able to answer all questions and get things done. Siri and Cortana you can have small talk with, as well as getting things done, so they are much harder to build. They took years and years of giant company’s efforts. Different companies that don’t have those resources, like Facebook, will build more constrained utility bots.”
In 1950, Alan Turing's famous article "Computing Machinery and Intelligence" was published, which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably—on the basis of the conversational content alone—between the program and a real human. The notoriety of Turing's proposed test stimulated great interest in Joseph Weizenbaum's program ELIZA, published in 1966, which seemed to be able to fool users into believing that they were conversing with a real human. However Weizenbaum himself did not claim that ELIZA was genuinely intelligent, and the Introduction to his paper presented it more as a debunking exercise:
Alternatively, think about the times you are chatting with a colleague over Slack. The need to find relevant information typically happens during conversations, and instead of having to go to a browser to start searching, you could simply summon your friendly Slack chatbot and get it to do the work for you. Think of it as your own personal podcast producer – pulling up documents, facts, and data at the drop of a hat. This concept can be translated into the virtual assistants we use on the daily. Think about an ambient assistant like Alexa or Google Home that could just be part of a group conversation. Or your trusted assistant taking notes and actions during a meeting.
From any point in the conversation, the bot needs to know where to go next. If a user writes, “I’m looking for new pants,” the bot might ask, “For a man or woman?” The user may type, “For a woman.” Does the bot then ask about size, style, brand, or color? What if one of those modifiers was already specified in the query? The possibilities are endless, and every one of them has to be mapped with rules.
This is the big one. We worked with one particular large publisher (can’t name names unfortunately, but hundreds of thousands of users) in two phases. We initially released a test phase that was sort of a “catch all”. Anyone could message a broad keyword to their bot and start a campaign. Although we had a huge number of users come in, engagement was relatively average (87% open rate and 27.05% click-through rate average over the course of the test). Drop off here was fairly high, about 3.14% of users had unsubscribed by the end of the test.
This is where most applications of NLP struggle, and not just chatbots. Any system or application that relies upon a machine’s ability to parse human speech is likely to struggle with the complexities inherent in elements of speech such as metaphors and similes. Despite these considerable limitations, chatbots are becoming increasingly sophisticated, responsive, and more “natural.”
The biggest benefit of having a conversational AI solution is the instant response rate. Answering queries within an hour translates into 7X increase in the likelihood of converting a lead. Customers are more likely to talk about a negative experience than a positive one. So nipping a negative review right in the bud is going to help improve your product’s brand standing.
Like apps and websites, bots have a UI, but it is made up of dialogs, rather than screens. Dialogs help preserve your place within a conversation, prompt users when needed, and execute input validation. They are useful for managing multi-turn conversations and simple "forms-based" collections of information to accomplish activities such as booking a flight.
Several studies accomplished by analytics agencies such as Juniper or Gartner  report significant reduction of cost of customer services, leading to billions of dollars of economy in the next 10 years. Gartner predicts an integration by 2020 of chatbots in at least 85% of all client's applications to customer service. Juniper's study announces an impressive amount of $8 billion retained annually by 2022 due to the use of chatbots.