Semantic Browsing
An algorithm to surf the meaning

Francesco Lentini - NKS 2007 Wolfram Science Conference

Every document and intelligent message contains a “secret map”. An equally intelligent algorithm can be used to decode this map and use it to tag, mark-up, summarise and generate hypertext links. This is called reading and interpreting text with a click, but we call it Semantic Browsing or "the machine to read".

Let us suppose that it is necessary to analyse a binary code signal originating from a remote region of cosmic space. All that we can see is a string of bits:

010100110110010101101101011000010110111001
110100011010010110001100100000010000100111
001001101111011101110111001101101001011011
1001100111

To be certain that this is not merely a random series of symbols we require a meaning detector, such as data-mining techniques. Unfortunately, data-mining operate by applying the syntax rules of known languages. However, at message-internal level, we do not even know whether any such rules exist, therefore we need a new kind of algorithm:

The Semantic Browsing (SB) algorithm attempt to overcome the semantic barrier at message-internal level. One way to understand the concept is to examine several messages where the meaning is already known. For instance, SB examines this document itself, trying to answers to a very complex question: What is (are) the most important information(s) contained in this document? And the result is 1 to 3 possible reading-paths (in order of rilevance):

1. message-internal
2. algorithm
3. meaning

Finally, SB examines a text consisting entirely of random phrases. And the answer is: NONE.

Even if we have a well working machine to read, this is an exciting work in progress. Target of the research is to reach an acceptable solution to one of the “really big questions” posed by the doyen of American physicists, John Wheeler: What makes meaning? Through the SB algorithm we are in search of the lost meaning, veiled in the documents of every author and every epoch.