A chatbot is an artificial person, animal or other creature which holds conversations with humans. This could be a text based (typed) conversation, a spoken conversation or even a non-verbal conversation. Chatbot can run on local computers and phones, though most of the time it is accessed through the internet.
Typical usage
Chatbot is typically perceived as engaging software entity which humans can talk to. It can be interesting, inspiring and intriguing. It appears everywhere, from old ancient HTML pages to modern advanced social networking websites, and from standard computers to fashionable smart mobile devices.
Chatbots talk in almost every major language. Their language (Natural Language Processing, NLP) skills vary from extremely poor to very clever intelligent, helpful and funny. The same counts for their graphic design, sometimes it feels like a cartoonish character drawn by a child, and on the other hand there are photo-realistic 3D animated characters available, which are hard to distinguish from humans. And they are all referred to as ‘chatbots’. If you have a look at our chatbot gallery, you will immediately notice the difference.
The term Chatbot is closely related to chat bot and chatterbot. Chatterbot is more popular in relation to chatbot who talk a lot, and is not necessary very intelligent in processing the user answers. Chat bot is used by technical people who consider the word ‘bot’ as a normal term for ‘robotised actions’, and for them ‘chat bot’ is a special kind of bot. The term Chatbot is actually the most popular amongst these three terms and has the broadest meaning.
Chatbot, when it plays its role as a virtual representative of an enterprise, is widely used by businesses outside of the US, primarily in the UK, The Netherlands, Germany and Australia. Additionally, the usage of this term is quite popular amongst amateur AI enthusiasts willing to spend vast amounts of time on their own intelligent creations (with diverse outcomes).
Chatbot Eliza can be regarded as the ancestor and grandmother of the large chatbot family we have listed on our website. As you can see in our directory tab, there are hundreds of online chatbots available in the public domain, although we believe hundreds of thousands have been created by enthusiastic artificial intelligence amateurs on platforms such as Pandorabots, MyCyberTwin or Personality Forge AI. Most of these chatbots give similar responses, the default response, and it appears to take a long time and patience to train a chatbot in another field of expertise and not all amateur developers are willing to spend these vast amounts of time. Most of the chatbots created this way are no longer accessible. Only a small portion of fanatic botmasters manage to fight their way out of the crowd and get some visibility in the public domain.
A well known example of a Chatbot is A.L.I.C.E. (Artificial Linguistic Internet Computer Entity), originally created by Richard Wallace in 1995 and extended since then. A.L.I.C.E. won many honors and awards in various NLP contests, such as Loebner prize, The Chatterbox challenge, and BCS Machine Intelligence Competition.[1]
A.L.I.C.E. was written within the frame of Artificial Intelligence Markup Language (AIML), an open standard for creating any kind of chatbot, also developed by Wallace. Most AIML interpreters are offered under a free or open source license. Therefore, many “Alicebot clones” populate the internet, having been created based upon the original implementation of A.L.I.C.E. and its AIML knowledge base. This video shows a speech as given by dr. Wallace about A.L.I.C.E., AIML and the chatbot history in general.
Since the steep rise of available hardware and software platforms lately, nowadays chatbots are available everywhere. Originally, they were very tight to computers, then exchangeable through tapes, discs and floppy discs, but since the Internet era they have been widespread. For example ancient chatbot Eliza is now also available on iPhone, while famous chatbot A.L.I.C.E. is available on Facebook.
Build your own chatbot!
Talking to a chatbot can be a lot of fun, and if you have the desire, dedication and skills to create, maintain and manage your own chatbot, you can do it. Whether you choose a fully stand-alone “virtual companion”, or take on the challenge of creating your own web-based chatbot, there are several options available to you, the prospective new botmaster, for creating a new chatbot. Nevertheless, first of all you have to choose between a stand-alone chatbot application, and a web-based chatbot.
Stand-alone or web-based chatbot?
The “stand-alone” application, where the chatbot runs on a single computer, integrates mostly some sort of system interface, allowing your chatbot to control certain aspects and functions of your computer, such as playing media files, or retrieving documents. It usually also has a graphical component built in, as well, in the form of an avatar (often female) that enhances interaction, thus improving user’s experience.
In general, the stand-alone chatbot has the advantage that it is simple to install and use, has an engaging graphical interface and an audio component including speech recognition.
However, such a bot is not “your own”, though there are certain degrees of configuration that help to personalise your bot. Besides, for the most part, these applications are not free, though most have a “demo” version.
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.
In general, the web-based chatbot has the advantage for you to have control over behavior, personality, and (free) hosting, though there are “premium” options available and personalization of content.
However, web based bots are not as easy to set up as a stand-alone chatbot application. Setting up a web-based chatbot requires at least minimal experience with HTML, JavaScript and Artificial Intelligence Markup Language (AIML). Additionally, any sort of “fancy” features, such as Text To Speech, or an animated avatar, would have to be created and integrated into your chatbot’s page, and certain features, such as voice recognition, are either unavailable, or are severely limited.
Available AIML interpreters
To create your own chatbot, you have to be familiar with PHP scripting language, MySQL database management, and a chatbot engine - AIML interpreter. There are several AIML interpreters, for example PHP AIML interpreter (Program O), Python AIML Interpreter (PyAIML), and Java AIML Interpreter (Chatterbean).
If you do not know how to start creating your chatbot, you can also use a list of AIML pattern/response templates used in ALICE Annotated AIML set, and incorporate it into your chatbot.
ChatScript could be useful for your stand-alone chatbot engine, because it is complete with its own unique scripting language, created by Bruce Wilcox.
Chatbot hosting companies
To create a web-based bot, you can choose several companies such as Personality Forge AI, MyCyberTwin or Pandorabots.
Let’s pick Pandorabots as an example, and get started. Setting up an account is both free and simple, and after loging in you will see a link labelled “Create a Pandorabot”. By clicking on this link you will be asked to provide the name of your chatbot, define your chatbot’s role and create its personality.
Your chatbot on Pandorabots uses AIML to store input patterns, output “templates”, and other data that the server uses to create the output that the users to your bot type in. In order for you to be able to alter the responses your chatbot give to any given input, you need to have at least a basic understanding of how AIML works.
If you would like to connect with many other people who did this before, please check our AI Zone forum.
Turing 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.
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.
The 19th annual edition of ‘The First Turing Test’, called Loebner Prize Contest, was held in 2009 in Brighton, UK. The following video report explains how the Turing Test is organized in practice. It presents the location, the people and the results of this famous contest.
Hugh Loebner is a founder of Loebner Prize Contest, being the annual edition of ‘The First Turing Test’. This video shows an interview with Hugh Loebner speaking about the history of this contest, its future and his personal involvement in this project.
Additionally, the video below traces the early chatbot history from Alan Turing, through Joseph Weizenbaum and Eliza, the Loebner Prize, the invention of the world wide web, and the work of George Kingsley Zipf.
Despite all efforts during almost half a century, most chatbots are still easily uncovered, but over the next decades they will definitely get smarter and finally we will distinguish human beings by them giving us silly answers as opposed to the much smarter chatbots. All of this will really start accelerating as soon as one single chatbot is smarter than one single human being. They will then be able to learn from each other, instead of learning from human beings, their knowledge will explode and they will be able to design even better learning mechanisms. In the long run, we will learn language from chatbots instead of the other way around.
Background
The term Chatbot is constructed of two words: chat and bot.
The word chat originates from mid- XV century and is a short form of the verb chatter. As a noun, it first appeared in 1520s. Chat room in the online sense is attested by 1994, from the days when America OnLine (AOL) ruled the Internet.[2]
The word robot is derived from the Czech noun robota meaning “labor”, and is an accomplishment of the cubist painter and writer Josef Capek, older brother of novelist and playwright Karel Capek. The word robot first appeared in 1920 in the Karel Capek’s play “RUR” (“Rossum’s Universal Robots”) and since then this play popularized the word invented by playwright’s brother.[3]
The word bot, in Internet sense, is a short form of robot and originates from XX century. The modern use of the word bot has curious affinities with earlier uses, e.g. “parasitical worm or maggot” (1520s), of unknown origin; and Australian-New Zealand slang “worthless, troublesome person” (World War I -era). The method of minting new slang by clipping the heads off respectable words does not seem to be old or widespread in English. Examples: za from pizza, zels from pretzels, rents from parents, are American English student or teen slang and seem to date back no further than late 1960s.[4]
Chatbot Eliza is generally recognized as the first ever artificial intelligence chatbot, which was developed by MIT Professor Joseph Weizenbaum in 1966. Eliza was implemented in SLIP (Symmetric List Processor), a processing language invented also by Joseph Weizenbaum. It worked by a simple parsing and substitution of key words into canned phrases.
Although Weizenbaum created his ELIZA thirty years before Internet became familiar to the general public, his creation is still alive and accessible to everyone. Watch the following video created by a youtube user IanProCastsCoUk, and see how the javascript version of Eliza emulates a Rogerian psychotherapist, responds on questions and leads simple conversations.
According to Richard Wallace, chatbots development faced three phases over the past 60 years. In the beginning, chatbot only simulated human-human conversations, using canned responses based on keywords, and it had almost no intelligence. Second phase of development was strictly associated with the expansion of Internet, thanks to which a chatbot was widely accessed and chatted with thousands of users. Then, the first commercial chatbot developers appeared. The third wave of chatbots development is combined with advanced technologies such as natural language processing, speech synthesis and real-time rendering videos. It comprises of chatbot appearing within web pages, instant messaging, and virtual worlds.
Examples of Chatbots
Chatbot pages
Although we use chatbot as the main synonym on this website, please do not be confused. There are more than 161 synonyms in use by academics, business and chatbot enthusiasts! It is simply a matter of reading between the lines.
Please check out our main directory with 1376 live chatbot examples (an overview as maintained by developers themselves),
our vendor listing with 253 chatbot companies
and chatbot news section
with already more than 368 articles! Our research tab contains lots of papers on chatbots, 1,166 journals on chatbots and 390 books on chatbots. This research section also shows which universities are active in the chatbot field, indicates which publishers are publishing journals on humanlike conversational AI and informs about academic events on chatbots. Also, check out our dedicated tab for awards, contest and games related to the chatbot field,
various forums like our AI forum by chatbot enthusiasts
and add any chatbot as created by yourself and your colleagues
to our chatbot directory. Please do not forget to register to join us in these exciting times.
A selection of pages on this website using 'chatbot':
Alternative usage of Chatbots
Alternative usage of the term Chatbot is related to what we described before, but having a physical, touchable ‘body’.
This video demonstrates a chatbot released in 1985 being a Wireless Robot with a Remote Control, internal tape recorder and a Serving Tray. He moves forward, turns, stops, speaks (and his eyes light up), and delivers objects in his hands or on a tray, all by remote control.[5]
On this picture you can see a ChatBot developed by an electronics engineer Imran Naeem Shaikh. It constitutes of a set of wireless chatting terminals that use 128x64 graphics LCD and Ericsson Mobile keyboards.[6]
161 synonyms to address humanlike conversational AI entities?
Comments
There are 2 comments on this article: