Future Wave Web Technology Blog

The fol­low­ing post appears on DailyBlogma, where I was a guest blog­ger, con­tribut­ing my first arti­cle ear­lier this March.
I want to talk about a topic that I find very excit­ing.  The roots of this tech­nol­ogy are in the area of Artificial Intelligence.  This is not just for the tech savvy out there.  This will have an impact on how every­one uses the web, over time.  The idea is to make the web smarter, or should I say, to make the soft­ware and com­put­ers that run the web or run on the web smarter.

We all use the web and com­put­ers to con­nect with oth­ers, to find infor­ma­tion, to share infor­ma­tion and so on.  If we just focus on the web, we can begin by say­ing that before the seman­tic web and related tech­nolo­gies, com­put­ers had no idea as to the mean­ing of what was on a web page.  Search engines did not speak our lan­guage, despite the fact that it might seem oth­er­wise.  For a long time peo­ple have been putting into Google ques­tions like we might ask another per­son.  It prob­a­bly seemed that Google under­stood our lan­guage.  However, for the most part, even up until recently, Google has only been look­ing at what we type into the search box and extract­ing key­words or key phrases.  Then it looks for web sites or web pages that con­tain those key­words or key phrases.  It should be noted that Google is start­ing to inte­grate some of these seman­tic web or seman­tic search fea­tures at the time of this writing.

One prob­lem has been that the web pages did not have any­thing on them that would help the search engine or any other pro­gram run­ning on the web, to under­stand the mean­ing of what exactly is on the web page.  Previously, I wrote an arti­cle on my blog enti­tled “Semantics and Syntax,” which can be read here. I spoke about the notion that in any lan­guage, and also when com­put­ers com­mu­ni­cate, there is a syn­tax ( in English this would be the gram­mar and such) and the seman­tics, the mean­ing of what we want to com­mu­ni­cate.  The Semantic Web is offer­ing a whole range of tools for embed­ding mean­ing into web pages and then cre­at­ing tools to use that infor­ma­tion in new ways… to make the web smarter, as it were.

Let’s take an exam­ple of a search I did recently.  I had intro­duced a soft­ware appli­ca­tion called Digsby, which inte­grates the fea­tures of numer­ous other chat pro­grams, online email addresses and social net­work­ing ser­vices.  She had remarked that she knew of a place named “Digsby” and she was curi­ous to remem­ber where it is located.  I went to the search engine Google and to Yahoo and put in terms like “Digsby and geo­graphic loca­tion,” among other key­word search terms and var­i­ous group­ings of the terms.  I even tried to tell the search engines to not include web pages about a soft­ware appli­ca­tion.  That would be done some­thing like this on Google: digsby -”soft­ware appli­ca­tion” which you will find doesn’t work too well (the dash – means not).  The first result is for the main page of the soft­ware appli­ca­tion, which I said I specif­i­cally did not want.  Even this does not work bet­ter in Google: digsby geo­graphic loca­tion -”soft­ware application

The same search at Hakia.com of digsby geo­graphic loca­tion will pro­duce a page that has at the top a Spelling sug­ges­tion: Digby geo­graphic loca­tion which when you click on it does find infor­ma­tion about a place named Digby in Nova Scotia, Canada.  I had mis­pelled my loca­tion but at least Hakia under­stood that I meant to find out about a place, a geo­graphic loca­tion named Digby.  It under­stood some­thing of the “seman­tics,” in other words, of what I was seek­ing, the meaning.

This doesn’t hap­pen through magic.  Web devel­op­ers will have to start putting seman­tic markup and uti­liz­ing seman­tic web tech­nolo­gies to make this pos­si­ble.  It is an excit­ing field and an excit­ing direc­tion for things.  We are hear­ing about things like “nat­ural lan­guage pro­cess­ing,” which involves actu­ally under­stand­ing the syn­tax and seman­tics of our lan­guage so that for exam­ple a search engine could actu­ally under­stand a ques­tion or request writ­ten in nat­ural language.

Technorati Tags: arti­fi­cial intel­li­gence, Canada, google, key­word search terms, nat­ural lan­guage pro­cess­ing, Nova Scotia, search box, search engine, search engines, seman­tic search fea­tures, seman­tic web, seman­tic web tech­nolo­gies, social net­work­ing ser­vices, soft­ware appli­ca­tion, Web devel­op­ers, Web Search The, web smarter, Yahoo