Human touch. Chatbots, providing an interface similar to human-to-human interaction, are more intuitive and so less difficult to use than a standard banking mobile application. They doesn't require any additional software installation and are more adaptive as able to be personalized during the exploitation by the means of machine learning. Chatbots are instant and so much faster that phone calls, shown to be considered as tedious in some studies. Then they satisfy both speed and personalization requirement while interacting with a bank.
“Beware though, bots have the illusion of simplicity on the front end but there are many hurdles to overcome to create a great experience. So much work to be done. Analytics, flow optimization, keeping up with ever changing platforms that have no standard. For deeper integrations and real commerce like Assist powers, you have error checking, integrations to APIs, routing and escalation to live human support, understanding NLP, no back buttons, no home button, etc etc. We have to unlearn everything we learned the past 20 years to create an amazing experience in this new browser.” — Shane Mac, CEO of Assist
I will not go into the details of extracting each feature value here. It can be referred from the documentation of rasa-core link that I provided above. So, assuming we extracted all the required feature values from the sample conversations in the required format, we can then train an AI model like LSTM followed by softmax to predict the next_action. Referring to the above figure, this is what the ‘dialogue management’ component does. Why LSTM is more appropriate? — As mentioned above, we want our model to be context aware and look back into the conversational history to predict the next_action. This is akin to a time-series model (pls see my other LSTM-Time series article) and hence can be best captured in the memory state of the LSTM model. The amount of conversational history we want to look back can be a configurable hyper-parameter to the model.
1. AI-based: these ones really rely on training and are fairly complicated to set up. You train the chatbot to understand specific topics and tell your users which topics your chatbot can engage with. AI chatbots require all sorts of fall back and intent training. For example, let’s say you built a doctor chatbot (off the top of my head because I am working on one at the moment), it would have to understand that “i have a headache” and “got a headache” and “my head hurts” are the same intent. The user is free to engage and the chatbot has to pick things up.
Build a bot directly from one of the top messaging apps themselves. By building a bot in Telegram, you can easily run a bot in the application itself. The company recently open-sourced their chatbot code, making it easy for third-parties to integrate and create bots of their own. Their Telegram API, which they also built, can send customized notifications, news, reminders, or alerts. Integrate the API with other popular apps such as YouTube and Github for a unique customer experience.
In a procedural conversation flow, you define the order of the questions and the bot will ask the questions in the order you defined. You can organize the questions into logical modules to keep the code centralized while staying focused on guiding the conversational. For example, you may design one module to contain the logic that helps the user browse for products and a separate module to contain the logic that helps the user create a new order.
Online chatbots save time and efforts by automating customer support. Gartner forecasts that by 2020, over 85% of customer interactions will be handled without a human. However, the opportunites provided by chatbot systems go far beyond giving responses to customers’ inquiries. They are also used for other business tasks, like collecting information about users, helping to organize meetings and reducing overhead costs. There is no wonder that size of the chatbot market is growing exponentially.
Companies use internet bots to increase online engagement and streamline communication. Companies often use bots to cut down on cost, instead of employing people to communicate with consumers, companies have developed new ways to be efficient. These chatbots are used to answer customers' questions. For example, Domino's has developed a chatbot that can take orders via Facebook Messenger. Chatbots allow companies to allocate their employees' time to more important things.
The trained neural network is less code than an comparable algorithm but it requires a potentially large matrix of “weights”. In a relatively small sample, where the training sentences have 150 unique words and 30 classes this would be a matrix of 150x30. Imagine multiplying a matrix of this size 100,000 times to establish a sufficiently low error rate. This is where processing speed comes in.
Chatbots – also known as “conversational agents” – are software applications that mimic written or spoken human speech for the purposes of simulating a conversation or interaction with a real person. There are two primary ways chatbots are offered to visitors: via web-based applications or standalone apps. Today, chatbots are used most commonly in the customer service space, assuming roles traditionally performed by living, breathing human beings such as Tier-1 support operatives and customer satisfaction reps.
At this year’s I/O, Google announced its own Facebook Messenger competitor called Allo. Apart from some neat features around privacy and self-expression, the really interesting part of Allo is @google, the app’s AI digital assistant. Google’s assistant is interesting because the company has about a decades-long head start in machine learning applied to search, so its likely that Allo’s chatbot will be very useful. In fact, you could see Allo becoming the primary interface for interacting with Google search over time. This interaction model would more closely resemble Larry Page’s long-term vision for search, which goes far beyond the clumsy search query + results page model of today:
There is a general worry that the bot can’t understand the intent of the customer. The bots are first trained with the actual data. Most companies that already have a chatbot must be having logs of conversations. Developers use that logs to analyze what customers are trying to ask and what does that mean. With a combination of Machine Learning models and tools built, developers match questions that customer asks and answers with the best suitable answer. For example: If a customer is asking “Where is my payment receipt?” and “I have not received a payment receipt”, mean the same thing. Developers strength is in training the models so that the chatbot is able to connect both of those questions to correct intent and as an output produces the correct answer. If there is no extensive data available, different APIs data can be used to train the chatbot.
“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.”
For example, ecommerce companies will likely want a chatbot that can display products, handle shipping questions, but a healthcare chatbot would look very different. Also, while most chatbot software is continually upping the AI-ante, a company called Landbot is taking a different approach, stripping away the complexity to help create better customer conversations.
The chatbot is trained to translate the input data into a desired output value. When given this data, it analyzes and forms context to point to the relevant data to react to spoken or written prompts. Looking into deep learning within AI, the machine discovers new patterns in the data without any prior information or training, then extracts and stores the pattern.
Not integrated. This goes hand-in-hand with the contextual knowledge, but chatbots often suffer from “death by data silo” where their access to data is limited. If a chatbot is “chatting with” a customer, they not only need to access the contextual data of their customer but also have access to every place where the answer to the customer’s question may reside. Product documentation site, customer community, different websites are all places where that answer can be.
This kind of thinking has lead me to develop a bot where the focus is as a medium for content rather than a subsitute for intelligence. So users create content much as conventional author, (but with text stored in spreadsheets rather than anywhere else). Very little is expected from the bot in terms of human behavious such as “learning”, “empathy”, “memory” and character”. Does it work?
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.”
Developed to assist Nigerian students preparing for their secondary school exam, the University Tertiary Matriculation Examination (UTME), SimbiBot is a chatbot that uses past exam questions to help students prepare for a variety of subjects. It offers multiple choice quizzes to help students test their knowledge, shows them where they went wrong, and even offers tips and advice based on how well the student is progressing.
One pertinent field of AI research is natural language processing. Usually, weak AI fields employ specialized software or programming languages created specifically for the narrow function required. For example, A.L.I.C.E. uses a markup language called AIML, which is specific to its function as a conversational agent, and has since been adopted by various other developers of, so called, Alicebots. Nevertheless, A.L.I.C.E. is still purely based on pattern matching techniques without any reasoning capabilities, the same technique ELIZA was using back in 1966. This is not strong AI, which would require sapience and logical reasoning abilities.