The “web-based” solution, which runs on a remote server, is generally able to be reached by the general public through a web page. It constitutes a web page with a chatbot embedded in it, and a text form is the sole interface between the user (you) and the chatbot. Any “upgrades” or improvements to the interface are solely the option and responsibility of the botmaster.
Of course, it is not so simple to create an interactive agent that the user will really trust. That’s why IM bots have not replaced all the couriers, doctors and the author of these lines. In this article, instead of talking about the future of chatbots, we will give you a short excursion into the topic of chatbots, how they work, how they can be employed and how difficult it is to create one yourself.
There has been a great deal of controversy about the use of bots in an automated trading function. Auction website eBay has been to court in an attempt to suppress a third-party company from using bots to traverse their site looking for bargains; this approach backfired on eBay and attracted the attention of further bots. The United Kingdom-based bet exchange Betfair saw such a large amount of traffic coming from bots that it launched a WebService API aimed at bot programmers, through which it can actively manage bot interactions.
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.
However, as irresistible as this story was to news outlets, Facebook’s engineers didn’t pull the plug on the experiment out of fear the bots were somehow secretly colluding to usurp their meatbag overlords and usher in a new age of machine dominance. They ended the experiment due to the fact that, once the bots had deviated far enough from acceptable English language parameters, the data gleaned by the conversational aspects of the test was of limited value.
The evolution of artificial intelligence is now in full swing and chatbots are only a faint splash on a huge wave of progress. Today the number of users of messaging apps like WhatsApp, Slack, Skype and their analogs is skyrocketing, Facebook Messenger alone has more than 1.2 billion monthly users. With the spread of messengers, virtual chatterbots that imitate human conversations for solving various tasks are becoming increasingly in demand. Chinese WeChat bots can already set medical appointments, call a taxi, send money to friends, check in for a flight and many many other.
Along with the continued development of our avatars, we are also investigating machine learning and deep learning techniques, and working on the creation of a short term memory for our bots. This will allow humans interacting with our AI to develop genuine human-like relationships with their bot; any personal information that is exchanged will be remembered by the bot and recalled in the correct context at the appropriate time. The bots will get to know their human companion, and utilise this knowledge to form warmer and more personal interactions.
The first formal instantiation of a Turing Test for machine intelligence is a Loebner Prize and has been organized since 1991. In a typical setup, there are three areas: the computer area with typically 3-5 computers, each running a stand-alone version (i.e. not connected with the internet) of the participating chatbot, an area for the human judges, typically four persons, and another area for the ‘confederates’, typically 3-5 voluntary humans, dependent on the number of chatbot participants. The human judges, working on their own terminal separated from one another, engage in a conversation with a human or a computer through the terminal, not knowing whether they are connected to a computer or a human. Then, they simply start to interact. The organizing committee requires that conversations are restricted to a single topic. The task for the human judges is to recognize chatbot responses and distinguish them from conversations with humans. If the judges cannot reliably distinguish the chatbot from the human, the chatbot is said to have passed the test.
Sometimes it is hard to discover if a conversational partner on the other end is a real person or a chatbot. In fact, it is getting harder as technology progresses. A well-known way to measure the chatbot intelligence in a more or less objective manner is the so-called Turing Test. This test determines how well a chatbot is capable of appearing like a real person by giving responses indistinguishable from a human’s response.