What+is+SLA+-+LSA+2

What is SLA? - Latent Semantic Analysis 2
The computer then operated logrithmically on the words (i.e., strings of characters) and their relationship or "dimensions" compared to other words in the various contexts (i.e., to other words/strings).

When given the synonym portion of the TOEFL, the machine approximated the average scores of EFL applicants to U.S. colleges. The model got 64.4% correct, and the students got 64.5% (Landauer & Dumais, p. 14).

This is all without the computer understanding the words tested semantically, and without being able to use grammar/syntax cues.

Landauer and Dumais feel that the machine //acquired// knowledge about synonymity "from the kinds of experience on which a human relies" (2004, p. 15). That is, the billions of neural networks in the brain can exploit both indirect inference and co-occurrence relations, both within and beyond a particular text.

The human brain of course is a billion times more powerful.

//NEXT//

Landauer, T. K., & Dumais, S. T. (2004). A solution to Plato's problem: The Latent Semantic Analysis theory of acquisition, induction and representation of knowledge. Available at http://lsa.colorado.edu/papers/plato/plato.annote.html.