seanlevan

I have tried replicating what you a talking about, but I haven't been able. When I ask him for a joke, he is quite funny. Do you have a screenshot to reproduce this?

What is wrong with his jokes? I have tried asking him a few and his responses are quite funny.

I have indeed heard about FreeHAL. It won "Most Popular" (in the past) in the same contest in which my bot most recently was awarded "Best New Bot". FreeHAL is now discontinued, last I've heard.

Though were did you hear that it's creator was 13-years-old during itself inception? I'm not doubting it, I just haven't found any online sources to validate that point.

For some reason, I'm not able to replicate the bug you caught. On my side, ACUMAN answers that question correctly.

I have encountered the same issue, but then again! Just continue building something, this time trying to fix the poor syntax practices that you have been caught with.

I am very indebted to my parents due to the way that I was raised and the freedom which being home-schooled permitted, but my parents are not familiar with the field of computer science and I must admit that I am entirely self-taught. This is because I came from a family of with a primarily literature-oriented and cultural background. I enjoy being raised in artistry.

Here is a Wiki page on my father: http://en.wikipedia.org/wiki/Eric_Le_Van

My mother is an educator and tutor. http://www.myriamlevan.com/

My sisters are also musicians, who are studying at Princeton university.

Thank you! That's a nice compliment.

For me, it was 5% reading, 95% hands-on experience, though it differs from person-to-person.

Those bugs are fixed and the algorithm regarding identifying countries and states in discussion has been improved.

As I've replied to other people: No AIML. My bot uses its own markup language custom-made to its needs that I call ACUMANSCRIPT. What makes it special is the backend, which is much more flexible and advanced then AIML (which focusing on exact string matching).

In fact, ACUMAN beat the ALICE bot in the last Chatterbox Challenge by over 20 points, winning the "Best New Bot" prize.

http://acuman.us/readmore.php

The model behind my project is not designed after human interaction, but rather a combination of what is the most efficient for me to maintain and best mimics human behavior.

http://acuman.us/readmore.php

Hi, I wasn't able to reproduce that glitch.

I do pursue programming, and contribute to open-source projects such as DuckDuckGo.

I also have a job as part of a web development and design team called http://www.whiskeyandwhiskey.com/.

I have quite a few opportunities for hands-on experience.

Mine is AI in the sense that it uses machine learning algorithms and corroborates it in a way that mimics human behavior. Maybe I put too much effort to the interface, but the interface took me a while.

Furthermore, my project does not end at the chatterbot element of it: it also collects useful psychometric data using text classification algorithms.

http://acuman.us/readmore.php

That's actually a glitch that I am fixing... desperately! Some of the backend APIs are down due to excessive requests, so I am trying to get them back up.

My chatterbot received the definition by WolframAlpha, per as what it's programmed. It found the entity was "sentence" and then looked for a definition. It does not simply grab whatever WolframAlpha response it can find.

Evidence for this lies in the fact that for the last hour, WolframAlpha was down for my bot due to excessive requests- and yet, no-one has noticed until this point- proving that there is significantly more to the algorithm then merely scraping their API.

There is a synonym directory programmed, as well as Named-enetity recognition.

I don't get what's new about any of this. I disclosed in this thread in other answers already the APIs I use,

I have yet to know any "intelligent" piece of artificial intelligence software that is not dependent whatsoever on external APIs. (Read: Siri, which is much more dependent on the WolframAlpha API then mine is). To me, it wouldn't be intelligent not to straddle the large resources of data available.

What you posted to, also, was hardcoded in WolframAlpha's system, which is not impressive.

Furthermore, try using WolframAlpha for conversation, and prepare to be disappointed. There's a lot of parsing going on in the backend on my system to make it work.

Yes. If you were in a noticeably bad mood, the bot might make a comment on it. It also picks on your hobbies and goals, and asks more questions about them or reminds you to follow through with them.

That's a funny exchange! The particularly odd thing is the fact that he missed the Named-entity recognition in some of those answers- including by not identifying that you were referring to the fact that you were moving to a state. He somehow interpreted it as an opinion. Let me check what exactly went on that prevented his correct behavior.

Thank you for expressing interest. You are correct, there are some issues that may be encountered with Firefox, particularly in a non-OS X or non-Windows environment. I am currently working on fixing those bugs.

Here is the URL: http://acuman.us/readmore.php

I decided that AIML was not useful to me because it was too rigid in syntax and was too static. This is particularly in the manner in which most AIML interpreters parse the syntax, making a rigid "if hello is in string, then say nice meeting you" syllogism (basically a beefed-up conditional statement) that essential has no room or place in actual artificial intelligence. I could have adjusted it to match my needs by creating my own interpreter, but I thought if I was going to accomplish that, why not create my own syntax that matches my needs better and has syntax that is even less convoluted and more focused on pattern-matching and machine learning?

I thought of releasing an API where you can code using the syntax of ACUMANSCRIPT- but I am unfortunately not prepared for open-sourcing ACUMAN's main architecture code due to it still competing in contests and fairs.

My favorite moments of my chatterbot is when he exhibits a sense of humor. :)

Thank you.

I believe that it must be a coincidence, or a way in which it deems an appropriate manner to react to your mood/state.

Do you have any specific case examples that are particularly off-putting?

Unfortunately, ACUMAN is closed-source due to the fact that it is actively being entered in competitive contests and trade fairs.

I believe my LinkedIn should be sufficient evidence...?

I don't understand your demand, though I suppose it is a compliment?

That's the interesting thing- I am not, unlike most chatterbot projects, using existing technologies and jumbling it together- a quick glance at the "read more" page on the technologies of ACUMAN will tell you otherwise.

Everything is made from scratch. From the ground-up. I could have used AIML (the AI version of XML), or anything I wanted. But instead, to make it unique and customizable to the demand of this project, I created my own markup language entitled ACUMANSCRIPT. Even the sentiment analysis algorithms are made from scratch by using Naive Bayens algorithms. The only APIs in use are those for some aspects of the knowledge base, which is a must in any machine learning or artificial intelligence project, as not leveraging the massive amount of data available on the internet would be a waste.

I sincerely doubt that we are anywhere near a flawless piece of artificial intelligence software, but this is not a result of people's lack of diligence in the field, but rather a testimony to it's complexities.

Google has made a short documentary explaining why natural language processing and machine learning are some of the hardest fields due to their surprisingly complex nature:

https://www.youtube.com/watch?v=yxxRAHVtafI

No - if you look up Blekko (which is a regular web search engine which had a free API), it just shut down (which is actually a bad thing for me). I was using it for researching and corroborating web results, which hinders part of the functionality of my bot.

Blekko was just bought by IBM a few days ago, so to answer your question, my bot does not use IBM's APIs. My bot was using it for web results, but now it doesn't work. I'm trying to find a free web search API as an alternative now that Blekko is shut down.

Thank you for participating in the survey, first of all!

I'll consider implementing one of those options. Thank you for your feedback.

Thank you for checking out ACUMAN.

I have fixed the glitch just now that prevented it from answering those questions normally.

While I understand where you are coming from, obviously the bot is not flawless, but it is ridiculous to compare our technology today to Eliza. ACUMAN uses a wealth of knowledge bases and natural language processing to comprehend and accurately give responses. Obviously, the field is invariably complex, but I find it absurd to say that it has increased so little, considering that it was never dreamed of that a bot would be able to answer the exact release date of a specific musical album, for instance.

It is still a work in progress, but I don't understand why it would be a huge turnoff that there was a simple grammatical error in the bot where he inadvertently prepended a contraction "it's" before the actual answer.

More specifically, science fairs, where I present my project abstract and convey the idea.

Thank you for your kind words and for checking it out!

That bug, along with others, have been fixed. (Also thanks to user "danieloaks" who contributed some code here on Hacker News.)