3. Now, since ours is a conversational AI bot, we need to keep track of the conversations happened thus far, to predict an appropriate response. For this purpose, we need a dictionary object that can be persisted with information about the current intent, current entities, persisted information that user would have provided to bot’s previous questions, bot’s previous action, results of the API call (if any). This information will constitute our input X, the feature vector. The target y, that the dialogue model is going to be trained upon will be ‘next_action’ (The next_action can simply be a one-hot encoded vector corresponding to each actions that we define in our training data).
This is great for the consumer because they don't need to leave the environment of Facebook to get access to the content they want, and it's hugely beneficial to Politico, as they're able to push on-demand content through to an increasingly engaged audience - oh, and they can also learn a bunch of interesting things about their audience in the process (I'll get to this shortly).
Botsify is another Facebook chatbot platform that helps make it easy to integrate chatbots into the system. Its paid subscription helps you in five easy steps. 1) Log into the botsify.com site, 2) Connect your Facebook account, 3) Setup a webhook, 4) Write up commands for the chatbot you are creating, and 5) Let Botisfy handle the customer service for you. If the paid services are a little too much, they do offer a free service that lets you create as many bots as your lovely imagination can dream up.
A rapidly growing, benign, form of internet bot is the chatbot. From 2016, when Facebook Messenger allowed developers to place chatbots on their platform, there has been an exponential growth of their use on that forum alone. 30,000 bots were created for Messenger in the first six months, rising to 100,000 by September 2017.[8] Avi Ben Ezra, CTO of SnatchBot, told Forbes that evidence from the use of their chatbot building platform pointed to a near future saving of millions of hours of human labour as 'live chat' on websites was replaced with bots.[9]
Pop-culture references to Skynet and a forthcoming “war against the machines” are perhaps a little too common in articles about AI (including this one and Larry’s post about Google’s RankBrain tech), but they do raise somewhat uncomfortable questions about the unexpected side of developing increasingly sophisticated AI constructs – including seemingly harmless chatbots.
Context: When a NLU algorithm analyzes a sentence, it does not have the history of the user conversation. It means that if it receives the answer to a question it has just asked, it will not remember the question. For differentiating the phases during the chat conversation, it’s state should be stored. It can either be flags like “Ordering Pizza” or parameters like “Restaurant: ‘Dominos’”. With context, you can easily relate intents with no need to know what was the previous question.
Feine, J., Morana, S., and Maedche, A. (2019). “Leveraging Machine-Executable Descriptive Knowledge in Design Science Research ‐ The Case of Designing Socially-Adaptive Chatbots”. In: Extending the Boundaries of Design Science Theory and Practice. Ed. by B. Tulu, S. Djamasbi, G. Leroy. Cham: Springer International Publishing, pp. 76–91. Download Publication
Ein Chatterbot, Chatbot oder kurz Bot ist ein textbasiertes Dialogsystem, welches das Chatten mit einem technischen System erlaubt. Er hat je einen Bereich zur Textein- und -ausgabe, über die sich in natürlicher Sprache mit dem dahinterstehenden System kommunizieren lässt. Chatbots können, müssen aber nicht in Verbindung mit einem Avatar benutzt werden. Technisch sind Bots näher mit einer Volltextsuchmaschine verwandt als mit künstlicher oder gar natürlicher Intelligenz. Mit der steigenden Computerleistung können Chatbot-Systeme allerdings immer schneller auf immer umfangreichere Datenbestände zugreifen und daher auch intelligente Dialoge für den Nutzer bieten. Solche Systeme werden auch als virtuelle persönliche Assistenten bezeichnet.
In 2000 a chatbot built using this approach was in the news for passing the “Turing test”, built by John Denning and colleagues. It was built to emulate the replies of a 13 year old boy from Ukraine (broken English and all). I met with John in 2015 and he made no false pretenses about the internal workings of this automaton. It may have been “brute force” but it proved a point: parts of a conversation can be made to appear “natural” using a sufficiently large definition of patterns. It proved Alan Turing’s assertion, that this question of a machine fooling humans was “meaningless”.
It won’t be an easy march though once we get to the nitty-gritty details. For example, I heard through the grapevine that when Starbucks looked at the voice data they collected from customer orders, they found that there are a few millions unique ways to order. (For those in the field, I’m talking about unique user utterances.) This is to be expected given the wild combinations of latte vs mocha, dairy vs soy, grande vs trenta, extra-hot vs iced, room vs no-room, for here vs to-go, snack variety, spoken accent diversity, etc. The AI practitioner will soon curse all these dimensions before taking a deep learning breath and getting to work. I feel though that given practically unlimited data, deep learning is now good enough to overcome this problem, and it is only a matter of couple of years until we see these TODA solutions deployed. One technique to watch is Generative Adversarial Nets (GAN). Roughly speaking, GAN engages itself in an iterative game of counterfeiting real stuffs, getting caught by the police neural network, improving counterfeiting skill, and rinse-and-repeating until it can pass as your Starbucks’ order-taking person, given enough data and iterations.
In our work at ZipfWorks building and scaling intelligent shopping platforms and applications, we pay close attention to emerging trends impacting digital commerce such as chatbots and mobile commerce. As this nascent trend towards a more conversational commerce ecosystem unfolds at a dizzying pace, we felt it would be useful to take a step back and look at the major initiatives and forces shaping this trend and compiled them here in this report. We’ve applied some of these concepts in our current project Dealspotr, to help more shoppers save more money through intelligent use of technology and social product design.

ELIZA's key method of operation (copied by chatbot designers ever since) involves the recognition of clue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses that can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY').[9] Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent".