AI Zone

Morti is ready for another round of testing

2010-06-26T16:08:41+01:00

Although I’ve had to take a break from the development of my chatbot, Morti, I’ve finally gotten everything on my “short to-do list” checked off, so I need to create another one, and for that I’d like some help. Please feel free to stop in and chat with Morti about whatever comes to mind. I’m more at the point of refining his responses than I am of fixing technical issues (though I’m fairly sure there are still some to work out. I just have to “find” hem). Also, I’d like you to report back here with any comments, questions, suggestions or ideas you may have. Thanks in advance.

The heart of A.I.

2010-08-07T22:48:46+01:00

.... in my humble opinion is…. IMAGINATION.

It seems to be an essential ‘ingredient’ to A.I. and especially chatbots.

In getting my bot to parse the sentence….

“The train being late, the soldiers missed their boat.”

I have it understand the connection between the to statements. *BUT* I had to basically give it a rule that relates these 2 concepts. I’m sure humans don’t need to be fed these rules that relate the two.

What would the bot need? Well, it would need to consider… It is probably true that the soldiers were going to use that same train to get to the place where the boat was. That is not stated in the sentence…. it seems that the bot will need an imagination, and to theorize, and from that, conclude on its own.

Now, instead of “calculating” these connections of statements with an imagination, what’s really wrong with just giving it a rule that connects these two sentences? I mean if it gets the job done the same way.

I have tested my bot with similar statements .. .

“The cab being late, the boys missed the show”
“My ride being late, I missed the concert”

Yes, it looks at the words in these sentences, and notices the same properties of the words, and the same type of connections.

The ultimate, or “ideal” way to do this of course, is if the bot had an imagination and ran a kind of “simulation” of reality, that I believe we humans have.

However, for a bot that can chat with you, and do useful things, I don’t think it is absolutely a requirement. I don’t know if a bot without an imagination could pass the Turing test though. If the bot had a kind of ‘internal world simulator’ or microcosm of the world, it could form these rules.

Then again, who is to say this rule I created that related those 2 statements in a cause/effect relationship isn’t itself a type of imagination, is there such a thing as ‘static’ and ‘dynamic’ imaginatons?

Thoughts anyone?

Regarding machine specifications for the 2011 contest

2010-08-08T01:49:40+01:00

As I’m sure everyone here well knows, I’m working on ways to make a version of Morti that will be able to compete in the Loebner Prize Competition, possibly in 2011, but more likely in 2012. Since I likely won’t’ be able to attend myself, I want to make it so that a USB flash drive can be inserted, and Morti will be ready to go. However, this means that I’ll need to have an understanding of what form the architecture of the machine he’ll be plugged into will be. Specifically, it would be good to know what OS platform it will have, what scripting language interpreters will be native to the system (e.g. PERL, PHP, Python, Ruby, etc.), availability of databases, if any (MS SQL, MySQL, Oracle, etc.), and other parameters, such as RAM.

Knowing this information will help me (or anyone else, as well) to determine what actions I need to take to be certain that Morti’s “installation” will be a smooth and painless process. Exact technical specs aren’t exactly required, but would be nice.

Also, will it be one computer per entrant? Or will Morti have to share resources?

My little chatbot project…

2010-05-28T04:04:49+01:00

Hi Everybody,
I’ve been away from Chatbots.org for a couple of months focusing on starting and maintaining an organic garden in the backyard. It’s been a great break from programming and has allowed me to think about my first chat bot program. The weather is beginning to get very hot and humid here in the Carolinas so I’m apt to spend much of my free time this summer inside at the computer.

Here’s a basic design spec.

Goal: Create a virtual character that lives in a 3D world that is 1km x 1 km. The world consists of natural features (trees, hills, streams), man-made features (buildings, power lines, etc.), and critters of various types. The virtual character communicates via simulated ‘text messaging’ with the human. It can answer various ‘where’ formatted questions in absolute and relative terms. It can obey simple exploratory commands related to its environment.

Purpose: I always like to ‘reinvent’ the wheel…and generally produce something with too many sides to roll correctly. However, now and then, even I get lucky. =) I simply wish to give this a go. It should be a good blend of my interests: game programming, gardening and the outdoors, and wanting to make a chat bot.

Development: I’ll write the code in C++ using Visual Studio. I’ll create data files using Excel. The initial application will be a simple console window. Graphics (DirectX) and sound will follow if the initial code is satisfactory. I don’t want to be distracted by the bells and whistles of such a project.

Design Objectives: (not listed in any particular order)

1) Create general object library that represents ‘general knowledge’ of the world such as trees, buildings, birds, etc. Library format will be defined and a tool developed to add knowledge.
2) Create a virtual world that draws upon the the general object library to create unique and varied instances of the objects. E.g. various types of trees at various heights and in various conditions.
3) Create virtual bot that has the ability and simulated ‘will’ to explore his world. NOTE: He’ll start off as a guy so my wife doesn’t become jealous or the time I spend with her. =)
4) Employ physics so the bot avoids obstacles. Includes simulated vision, audio, and olfactory senses. This means that a module or interface must be developed between the virtual bot and the virtual world to simulate senses.
5) Implement curiosity mode so he stops, observes, and stores details in short-term memory. Initially objects in the world are static but eventually will move (critters) or change (tree colors).
6) Develop ability to respond to questions such as:
a) Where is the gray hut?
b) Where is the car?
c) What is that in the tree?
d) What is that behind the building?
e) Where are you?
f) Where are you going?
g) Where does the eagle live?

Limitations: The focus is upon the location of the bot and things in his virtual world, the use of prepositions and other means of specifying relative locations and the bots orientation in the world. No emphasis will be placed on other aspects of chatting such as general conversation, abstract concepts, wit and sarcasm, etc. Perhaps later if this actual works!

That’s about it. I would like to work on this over the summer months and conclude in the fall.

If you have suggestions or questions, please let me know. I’m still in the ‘thinking’ part of this project and have yet to write any code. I have a significant amount of ‘infrastructure’ to create so that the bot has the capacity to ‘grow’ along with its virtual world.

Regards,
Chuck

Simple Perl Examples

2010-07-23T14:09:41+01:00

Rather than have code samples scattered all over the forums, I’m creating this topic to serve as a collection of simple scripts.

These samples are not meant to be full solutions - rather, think of them as code “snippets” - to get you started.

This example is a tool to convert numbers (integers only) between 0 and 999,999 into words. Example, “593” returns “five hundred ninty three”.

Download here >> http://www.geekcavecreations.com/?downloads—click “Perl Numeric Examples”

for unix, you need to run it through “dos2unix” or “fromdos” to strip out the CR-LF’s.

That zip (or tar ball) file also contains a script to convert the other way (‘two hundred and nine’ input, returns 209).

Building intelligent chatbots without voice.. Not possible???

2010-08-16T21:57:24+01:00

Today I was thinking about intonation and meaning in sentences (from wikipedia):

“I never said she stole my money” - Someone else said it, but I
didn’t.
“I never said she stole my money” - I simply didn’t ever say it.
“I never said she stole my money” - I might have implied it in some
way, but I never explicitly said it.
“I never said she stole my money” - I said someone took it; I didn’t
say it was she.
“I never said she stole my money” - I just said she probably borrowed
it.
“I never said she stole my money” - I said she stole someone else’s
money.
“I never said she stole my money” - I said she stole something, but
not my money.

And I was wondering myself: how can we ever creating intelligent text based chatbots without using voice?

Applied Problems, an AI evaluating standard for chatbot.

2010-09-06T00:05:37+01:00

Before we request the chatbots to chat like human, there are many practical targets.
Applied problems may be a good choice to evaluate the AI level of chatbots.

For example

The cost of picture frame M is $10.00 less than 3 times the cost of picture frame N. If the cost of frame M is $50.00, how much is the cost of frame N?

The applied problems may be from simple to hard.

Challenging issues in NLP

2010-09-01T19:28:09+01:00

Some tricks used in LP, as I remembered remotely, are something like “which is bigger, Belgium or apple?” and “which is nearer, the Queen or the Queens street?” and “If we shake hands then what is in your right hand?”

These are good and reasonable tricks. Yet in my own design and development of chatbot I found Quotation is very difficult, with or without quotation marks. For example, Tom said Jack already told Sarah to call Peter…and two other most difficult issues to me are comma and “and”. These two little and common symbols are driving me crazy! Try parse “Tom knew Mary and Jack knew Sarah”

To me the only solution is a process of guess-evaluate-adjust but then there is no best answer but just valid options. Natual language is an art, anyway, esp. those stuff like flirt, joke, poem, political correct…

Or shall we design a lite version of English called “Concise English” and force everybody to use it with computer?

CLUES

2010-08-10T23:03:03+01:00

My current status on my CLUES (complex language understanding execution system) engine is…

INPUT: “While we were walking through the tunnel, we picked up a wallet.”

*Processing time: 4 seconds (for 13 word input, 90 parse trees generated in ./gis:).
* 60 subordinate-conjunction-multi-simple-sentence(s), 30 subordinate-conjunction-simple-sentence(s)

So, at this point, it can take in a sentence like the one given above and consider all possible grammatical interpretations. We see here that “While we were walking through the tunnel, we picked up a wallet.” can be thought of by the engine a total of 90 ways, 60 involving multiple sentences, and 30 as just simple-sentences.

In grammar, a “simple sentence” is one in which there is one subject and one predicate. The subject may have any number of nouns, the predicate may have any number of verbs and any number of predicate nouns or predicate adjectives.

Aside from a “simple sentence” there is compound sentence, complex sentence and complex-compound sentences.

A compound sentence is simply one or more simple sentences connected together via a “conjunction”. Examples of conjunctions are “and”, “or”, “but”.

A complex sentence is one in which you have a simple sentence which serves as the “main clause” and one or more additional simple-sentences that are called “subordinate clauses”.

My bot can now understand complex sentences such as

“I ate the meal that she cooked”

and parse it so that it understands that it is, as a whole, a complex sentence, with the main-clause (a simple sentence) of “I ate the meal”, and this complex sentence contains the subordinate clause (another simple-sentence) of “she cooked” ... the parse tree that is generated indicates the word “that” is the subordinate conjunction that connects them.

Sentences like this, however, generate many parse trees, and the way my bot selects the correct one, is to find which combinations of words have a “real world meaning”. For example, the predicate “ate a sandwich” makes sense to the bot since it knows that “sandwich” can be connected to “ate” by the relationship that, in a sentence, “sandwich” can be the direct compliment noun of a predicate which has a verb of “ate”.

My bot relies heavily on grammar, and also ‘real world’ knowledge and rules to help it select the single parse tree amongst the (sometimes) thousands of possible parse trees.

So far, results are extremely promising.

Clarification of rules

2010-06-21T17:35:02+01:00

I will be submitting my software for the 2011 Loebner contest. I’ve taken quite a different approach to AI and believe mine may have a fair chance of passing the Turing test.

I just wanted to clarify some of the rules as I’ve been concerned about the idea of it becoming a guessing game (a 50/50 coin flip) when the judge cannot determine which one is a computer. Is the scoring system set up in such a way that both can be judged as equally human? And if so, can the computer win the contest for being equally rated human? (or must it somehow prove to be “more human than human?”)

Thank you for your time,

Bobby