Semantic Hackers need NLP (Natural Language Processing), PROLOG and Assembly Language…

Image via Wikipedia

Semantic Hacker is a cool blog (and site) about the Semantic Web. I’ve placed them in my Web 3.0 blogroll today. They are offering an API (Application Programming Interface in geek-lingo) that can be integrated in Semantic Web applications using “Concept-Spaces”, based on weighted keywords.

However, an attempt I made to run their on-line test proved immediately and conclusively that their innovative API badly needs (Prolog-based?) Natural Language methods (NLP) of parsing and understanding human text. Without such methods, I’m afraid that the Semantic Hacker’s API… sucks! (Although this failure is occasional; most of the time the API test being quite successful). You can check this out by looking at the text I submitted to their on-line test, together with their (rather off-topic) results (copied and pasted from their test-form page):

Input Text Cut and paste your own text into this area.

Suppose there is an Internet Community with just one moderator; and that every person in the community keeps himself moderated: some by moderating themselves, some by obeying the (one and only) moderator. It seems reasonable to imagine that the moderator obeys the following rule: He moderates all and only those members of the community who do not moderate themselves. Under this scenario, we can ask the following question: Does the moderator moderate himself?

Simplified Semantic Signature®

…/EverQuest_Games/EverQuest/Server_Specific 38

…/Space_Combat/Star_Wars_Games/Star_Wars_Galaxies/Clans_and_Guilds 26

Society/Philosophy/Chats_and_Forums 24

Home/Family/Pregnancy/Chats_and_Forums24

Arts/Literature/Authors/Blake,_William 23

Related Wikipedia Articles

1.) Moderate

2.) Quarterdeck

3.) Becket (disambiguation)

4.) Quarterdeck Office Systems

5.) Quarterdeck Cleansweep

6.) Edward Grim

7.) Roger de Pont L’Evêque

8.) Jolly Cola

9.) Welton Becket

10.) Becket (film)

(end of test-results copied-&-pasted from Semantic Hacker)

Well, one can easily verify that… absolutely NONE of these results have any connection to the original text submitted: It was a text about moderation (aka private censorship), paraphrasing the well-known Logic Paradox (originally by Bertrand Russell) called “The barber’s paradox”, as explained in my blog-post “The Moderator’s Paradox” (a barber’s paraphrase).

Of course, if the Semantic Hacker’s API could understand the word “moderate” as a verb (instead of an adjective) then perhaps it could come up with more useful results. However, I am reluctant to accept the efficacy of methods based on dictionary-terms and concepts alone, without proper parsing (even the partial parsing of noun phrases as a minimum prerequisite).

NOTE: Parsing can also be done in Assembly Language, linked to Prolog or Java (or another programming language). Assembly Language Code for parsing and data-mining is a necessity, despite the high speed of modern CPU’s. Of course -rather sadly- few people write Assembly code today (and I am one of them, e.g. here).

• Assembly Language is necessary highly beneficial because of the huge amount of Data that needs to be processed: The Entirety of the Web, in fact. Even the fastest CPUs and the fastest programs are simply not enough !
• PROLOG (and Natural Language Programming – NLP) is also (even more) necessary, for the reasons explained previously (and elsewhere).
• Use of PROLOG turbo-enhanced with Pure Assembly Language is my personal choice for most programming, in the last 18 years or so (e.g. as in http://omadeon.com/alc)

Related articles

• Web 3.0 Through The Ages [via Zemanta]
• Is Keyword Search About To Hit Its Breaking Point? [via Zemanta]
• Meaning-Based Web and Web 3.0 [via Zemanta]
• PROLOG has (almost) the same Expressive Power as Human Language [in this blog]
• Ted Nelson criticizes today’s Web, proposing [in this blog]

.