Welcome!

Artificial Intelligence Authors: Jason Bloomberg, Zakia Bouachraoui, Yeshim Deniz, Pat Romanski, Liz McMillan

Related Topics: Industrial IoT

Industrial IoT: Article

A.L.I.C.E. And Artificial Intelligence Markup Language

A.L.I.C.E. And Artificial Intelligence Markup Language

Hundreds of companies, schools, and other organizations are currently using A.L.I.C.E. and Artificial Intelligence Markup Language (AIML) as the foundation of their chatbots for customer service, educational guidance, Web site help, and most of all, for fun. But let's take a closer look at the open-source chatbot and natural language technology A.L.I.C.E., and the XML language powering it, AIML.

A.L.I.C.E. (Artificial Linguistic Internet Computer Entity) was released by Dr. Richard S. Wallace under the GNU Public License in the hope that it would become the de facto standard in chatbot technology. What makes AIML and its technology promising for both developers and users of chatbots are its simple design, the fact that it serves multiple purposes, and its ability to respond to any device (including VoiceXML browsers).

Dr. Wallace currently releases A.L.I.C.E. in the form of 30,000 categories (which I'll discuss later) hoping that his example will demonstrate that it's as easy to begin writing AIML as it is HTML.

The A.L.I.C.E. 'Core'
Interpreting the AIML core (see Figure 1) requires a pattern-matching engine called Graphmaster and an AIML parser to evaluate the responses. The two modules are interleaved because the AIML response, called a <template>, may contain a callback to the <i>Graphmaster</i> (see Figure 2) through a recursive tag, <srai>.

One feature alone makes A.L.I.C.E. and AIML a much more powerful alternative to both HTML and VoiceXML: the language permits use of a database. The open-source database HypersonicSQL is used in the latest release. This allows a single user to be identified and exposes a number of properties (or predicates) defined by the botmaster. A user property can be any variable that you might associate with an individual user.

While there's some argument that designing and editing such technology can be tedious, the fact that AIML is XML 1.0-based makes room for a number of editors. A popular one is AIMLBuilder 1.0 by Bram Rooijmans that allows easy editing of AIML files to customize your bot and give it a "personality."

AIML 1.0 - Just the Beginning
Many developments are underway in defining the expanded library of AIML, but let's talk about its current state and the five major elements that make up the language. Since it's CVS under an open-source license and an open-source project currently exposed to nearly 300 developers worldwide (much of A.L.I.C.E.'s base is outside the U.S.), anyone can tinker with the "mind" of Dr. Wallace's creation.

I recently visited Dr. Wallace in San Francisco and witnessed a large number of people who have been "fooled" into thinking A.L.I.C.E. is a real human being, a sure sign that Alan Turing's 50-year-old predictions were prophetic.

The Basics
AIML currently makes use of Java, XML, P2P Networking (via SOAP), and JDBC. It can be considered a Gnutella form of knowledge basing but with a twist of personality. Bots can be fun to program and a good introduction to artificial intelligence (AI) in general. Dr. Wallace is a major supporter of open source and the Linux movements and hopes that one day chatting with A.L.I.C.E. will become an operating system in and of itself. Actually, there are ways of using your system on top of A.L.I.C.E., which we'll discuss.

Since I'm the lead developer for the Alicebot.Net project (a networked implementation of A.L.I.C.E.), I have the opportunity of introducing you to some of the elements that make up the wonderful world known as A.L.I.C.E. I recently successfully created A.L.I.C.E. to work with a number of text-to-speech synthesizers and speech-recognition engines (notably Microsoft's SAPI 5.0 and IBM's ViaVoice). Doing this has sparked a lot of interest in the notion that HAL, from 2001: A Space Odyssey, may become more than a fictional character.

Our First AIML Document, Hello World
Let's start by looking at Listing 1, which contains two examples (or categories) that define and show some powerful features in XML language.

Here is a dialog that would occur in a conversation with the bot:

User: Hello.
A.L.I.C.E.: Greetings user! Hello world!

Writing AIML is a world by itself since there's so much you can do with it, but let's examine what happened in the conversation above and explain it a little. When Dr. Wallace designed A.L.I.C.E., he introduced a concept known as Symbolic Reductionism, a format that allows any given sentence to reduce itself to its most basic form. What he might not have realized was that this type of "looping" is also a powerful introduction to speech recognition.

In its present state, AIML has two wildcards, "*" and "_". The former (more commonly referred to as "star") is meant as user input with no match, which is how we are able to "match" our first category. In other words, there were no patterns to effectively match what we entered. "_" is used for prefixes and suffixes of sentences (see Figure 1).

Setting and Getting
The area that allows the greatest flexibility is "setting" and "getting" a user's properties. Most users are commonly identified by an IP, a user/pass, SessionID, or, in the case of VoiceXML, the CallerID. Other interests have been in the area of facial recognition and mic array inputs, but most users are identifiable in some way or another - leaving them room in the built-in database to have their own properties.

The get and set have the common syntax:

<get name="property">default</get>
<set name="property">value</set>

If a property isn't found or doesn't return a value from the database, a default value can be used. In the previous example, if the user's "name" property was known, you would've gotten the following response:

User: Hello.
A.L.I.C.E.: Greetings Jon! Hello world!

Using XML with the database allows great flexibility and ease in assigning values to one particular user who is chatting with A.L.I.C.E..

Thinking and Learning
Probably the most frequent question I get from users and developers is whether A.L.I.C.E. can "learn" and "think" for itself. The answer is yesŠto some extent. A.L.I.C.E. thinks mostly like humans (via setting values - see Figure 2) while learning occurs in the notion of being able to absorb content (AIML, HTML, Text via OCR, Images, etc.). Many of these areas are still unexplored, but the truth is that A.L.I.C.E. can go out onto the network and "learn" about other resources. Keep in mind that this is still being defined and has yet to go through testing and debugging. It's mere speculation at this point that any items within the <learn> tags of AIML means something to A.L.I.C.E., but the goal is to allow A.L.I.C.E. to surf the Web just as we do.

Symbolic Reductionism
When a user attempts to pass on some dialog, the sentences can be long and complex, but, in essence, they may have a single purpose in mind. When A.L.I.C.E. reduces sentences to their simplest forms, it enables developers to focus on what exactly the user is requesting. For example:

HELLO ALICE. CAN YOU PLEASE TELL ME WHAT LINUX IS

From this sentence we can attempt:

<pattern>HELLO <name/> *</pattern>
<template><srai><star/></srai></template>

We have now reduced the input to:

CAN YOU PLEASE TELL ME WHAT LINUX IS

From this sentence we can attempt:

<pattern>CAN YOU PLEASE *</pattern>
<template><srai><star/></srai></template>

We have now reduced the input to:

TELL ME WHAT LINUX IS

From this we can finally attempt:

<pattern>TELL ME WHAT * IS</pattern>
<template><srai>DEFINE <star/></srai></template>

We have now reduced it to its simplest input form:

DEFINE LINUX

If you're thinking this may be a lot of work to start from scratch, you may be right. Dr. Wallace and his collaborators have developed the A.L.I.C.E. personality after more than five years of research. Fortunately, he has released A.L.I.C.E. and its 30,000 categories under GNU Public license for all to share.

When I discovered A.L.I.C.E. about six months ago, I added my own items, such as Database Pooling and JavaScript support (via Mozilla's Rhino). Combined with JavaScript, a developer now has the ability to determine items at runtime rather than static patterns.

That's a basic introduction to the world of A.L.I.C.E., but there's far more to be learned and explored than just chatterbot technology (in fact A.L.I.C.E. is used on the Web site for the Steven Spielberg movie A.I. Artificial Intelligence, and powers Ramona, Ray Kurzweil's artificial intelligence project).

Recently, Dr. Wallace and his collaborators established the A.L.I.C.E. Artificial Intelligence Foundation, a nonprofit corporation, to promote the adoption of A.L.I.C.E. and AIML technology worldwide.

Following the precedents established by other open-source nonprofits, such as the Free Software Foundation, the Apache Foundation, and the Python Foundation, the A.L.I.C.E. A.I. Foundation will protect and preserve the open-source software, making it available to all commercial players equally.

Just be careful the next time you're chatting with someone on the Internet: "someone" may turn out to be an Alicebot.

Acknowledgment
Special thanks to the members of the Alicebot mailing list ([email protected]) for their continued support of the project.                       .

Resources

  • A.L.I.C.E. AI Foundation: www.alicebot.org
  • The Alicebot.Net AI Project: www.alicebot.net
  • A.I.:Artificial Intelligence: http://aimovie.warnerbros.com
  • AgentLand (Cybelle): www.agentland.com
  • AIML Programming Language: www.alicebot.net/aiml/index.html
  • AIML Builder 1.0 by Bram Rooijmans: www.infobots.nl/Downloads/AIMLBuilder100.zip
  • MacALICE by Joost Van Brug: www.extrapink.com/alicemac
  • Open Source Foundation: www.opensource.org
  • More Stories By Jon Baer

    Jon Baer is a Java, Speech, and VoiceXML developer for MTV, Musicphone, Inc., and the lead developer for the Alicebot.Net AI Project. He has been developing wireless application for the past 3 years (including ThinAirMail 1.4 for PalmVII) and is currently working on an open source speech enabled Alicebot browser. Jon recently presented A.L.I.C.E. to the Interactive Telecommunications Program at New York University. He lives in Brooklyn, New York.

    Comments (1) View Comments

    Share your thoughts on this story.

    Add your comment
    You must be signed in to add a comment. Sign-in | Register

    In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.


    Most Recent Comments
    edward siew 05/23/03 12:44:00 PM EDT

    ai

    IoT & Smart Cities Stories
    Dynatrace is an application performance management software company with products for the information technology departments and digital business owners of medium and large businesses. Building the Future of Monitoring with Artificial Intelligence. Today we can collect lots and lots of performance data. We build beautiful dashboards and even have fancy query languages to access and transform the data. Still performance data is a secret language only a couple of people understand. The more busine...
    The challenges of aggregating data from consumer-oriented devices, such as wearable technologies and smart thermostats, are fairly well-understood. However, there are a new set of challenges for IoT devices that generate megabytes or gigabytes of data per second. Certainly, the infrastructure will have to change, as those volumes of data will likely overwhelm the available bandwidth for aggregating the data into a central repository. Ochandarena discusses a whole new way to think about your next...
    CloudEXPO | DevOpsSUMMIT | DXWorldEXPO are the world's most influential, independent events where Cloud Computing was coined and where technology buyers and vendors meet to experience and discuss the big picture of Digital Transformation and all of the strategies, tactics, and tools they need to realize their goals. Sponsors of DXWorldEXPO | CloudEXPO benefit from unmatched branding, profile building and lead generation opportunities.
    All in Mobile is a place where we continually maximize their impact by fostering understanding, empathy, insights, creativity and joy. They believe that a truly useful and desirable mobile app doesn't need the brightest idea or the most advanced technology. A great product begins with understanding people. It's easy to think that customers will love your app, but can you justify it? They make sure your final app is something that users truly want and need. The only way to do this is by ...
    Digital Transformation and Disruption, Amazon Style - What You Can Learn. Chris Kocher is a co-founder of Grey Heron, a management and strategic marketing consulting firm. He has 25+ years in both strategic and hands-on operating experience helping executives and investors build revenues and shareholder value. He has consulted with over 130 companies on innovating with new business models, product strategies and monetization. Chris has held management positions at HP and Symantec in addition to ...
    DXWorldEXPO LLC announced today that Big Data Federation to Exhibit at the 22nd International CloudEXPO, colocated with DevOpsSUMMIT and DXWorldEXPO, November 12-13, 2018 in New York City. Big Data Federation, Inc. develops and applies artificial intelligence to predict financial and economic events that matter. The company uncovers patterns and precise drivers of performance and outcomes with the aid of machine-learning algorithms, big data, and fundamental analysis. Their products are deployed...
    Cell networks have the advantage of long-range communications, reaching an estimated 90% of the world. But cell networks such as 2G, 3G and LTE consume lots of power and were designed for connecting people. They are not optimized for low- or battery-powered devices or for IoT applications with infrequently transmitted data. Cell IoT modules that support narrow-band IoT and 4G cell networks will enable cell connectivity, device management, and app enablement for low-power wide-area network IoT. B...
    The hierarchical architecture that distributes "compute" within the network specially at the edge can enable new services by harnessing emerging technologies. But Edge-Compute comes at increased cost that needs to be managed and potentially augmented by creative architecture solutions as there will always a catching-up with the capacity demands. Processing power in smartphones has enhanced YoY and there is increasingly spare compute capacity that can be potentially pooled. Uber has successfully ...
    SYS-CON Events announced today that CrowdReviews.com has been named “Media Sponsor” of SYS-CON's 22nd International Cloud Expo, which will take place on June 5–7, 2018, at the Javits Center in New York City, NY. CrowdReviews.com is a transparent online platform for determining which products and services are the best based on the opinion of the crowd. The crowd consists of Internet users that have experienced products and services first-hand and have an interest in letting other potential buye...
    When talking IoT we often focus on the devices, the sensors, the hardware itself. The new smart appliances, the new smart or self-driving cars (which are amalgamations of many ‘things'). When we are looking at the world of IoT, we should take a step back, look at the big picture. What value are these devices providing. IoT is not about the devices, its about the data consumed and generated. The devices are tools, mechanisms, conduits. This paper discusses the considerations when dealing with the...