Hello,

We are pleased to invite you to try our Mnemoo first API for
Question/Answering in Natural Language (and standard keywords-based query)
for your chatterbot, virtual assistant and other cool products.

Info are here:

  http://www.intellexere.com/en/ikb/api/mno/qab/v1/mnemoo-question-answering-api-v1-getting-started
  http://www.intellexere.com/en/blog/post/introducing-the-sentiment-analysis-and-mnemoo-question-answering-api
  http://www.intellexere.com/en/blog/post/intellexere-java-sdk-0.1-is-now-available
  http://www.mnemoo.com
  http://www.complexityintelligence.com

Complexity Intelligence, LLC
http://www.complexityintelligence.com

If we may compare notes and share design information here—a True AI way to accomplish Q&A (question and answering) is to conceptualize the words involved and to let the AI respond from its cumulative knoweldge base.

http://www.scn.org/~mentifex/AiMind.html in JavaScript for Internet Explorer—updated today on Sat.12.NOV.2011 with special NounPhrase code to handle irregular English nouns—invites the user to teach the artificial Mind new concepts by asking and answering questions about previously unlearned nouns. Whosoever wishes may freely copy these AI Q&A techniques. -Arthur

Ignore Arthur’s spam. He does this on most threads. Incidentally Arthur, I tried your link and it couldn’t respond to the most basic of questions. I notice the user manual starts: “Not only using the AI Mind, but mere knowledge of its existence, poses an existential risk to the human species.” and I would strongly advise you seek psychiatrict help.

Alessio - I tried a few questions out on the mnemoo link as was pleasantly surprised. It could answer all of the ones I posed to it: “What flavour is tomato soup”, “Who was the first man on the moon” and “what colour is an orange”.

The other links want me to sign up as a developer and I wasn’t happy about doing that but nice work on the other link.

Thank you Steve for your positive reply.

Developers link is only intented for who is interested in embedding the Mnemoo engine inside their applications through our API. I apologize if I was not clear about that.

About Mnemoo, this is only the first step, and we’re very happy about traffic that is growing at a fantastic rate, and I hope this trend will countinue   This is, indirectly, a very good feedback on the Deep Informed Analysis theory (used in Mnemoo) for Natural Language Processing, that we want to “export” as soon as possible to the Virtual Assistant world with dedicated products. We’re working on that.

There is a lot of work to do, so any feedback is really appreciated.

HI Allessio,

Interesting topic! Once upon a time we’ll need a chabot for Chatbots.org as well. I’d love to connect to a service like this. I don’t care where the answer comes from, as long as it’s correct.

Any thought of adding a Javascript/JSON api?

@Erwin: Thanks for your reply. We’re happy to assist you connecting Mnemoo to the web site chatterbot. Definitely, this is a good choice for the web site

@Merlin: Yes, it’s a high priority task.

I am looking forward to the JS API as well. Currently I am data mining and that involves a whole lot of server side parsing and latency which is defeating my purpose. It would be great to query a knowledge base and add that information to my own system’s database for future user queries.

The Mnemoo Q&A API is currently accessible by any programming language that is able to send an HTTP request and parse the XML result. In JavaScript this can be done, right now, using JQuery in few lines of JS code.

For the http request format and parameters:
http://www.intellexere.com/en/ikb/api/mno/qab/v1/mnemoo-question-answering-api-v1-getting-started

JSON will be added soon as result format, so you can choose between XML and JSON (and RDF for some services).

@Laura, this seems interesting, can you explain something more (here, private msg, or a new thread if is OT within current thread).

If you develop a chat bot and you want to integrate QA into it you have a variety of choices:

1 - Build/store/curate your own knowledge base. (Lots of work, as I am sure you know)

2 - Use server side processing to accept a query and search for an answer. You could screen scrape a search engine request or you might use a search engine API. If you use a search engine, the returned response may include the answer, but often does not have it in the form of an answer (it might be a list of links and a text blurb). The AI would need to parse the search engine response and try to distill an answer. This approach often suffers from lag time as the query round trips between the bot-host-search engine and back.

3 - Use cross site scripting from the client. This may be faster but it can be fragile if the bot uses an Iframe. It is subject to changes in website policies (does the search engine allow results in Iframes), and even with a direct API may require filtering of the responses.

#3 is the approach I have used with Skynet-AI.

Alessio Paolucci - Nov 16, 2011:

We’re happy to assist you connecting Mnemoo to the web site chatterbot. Definitely, this is a good choice for the web site

Thanks Alessio! We’ll come back to this next year!