{ information making sense || making sense of information }
IT has been quiet on the SALSAdev blog for a moment. Well we have been busy putting together the pieces of our latest semantic prototype, news.NET. Please read on after the jump, but first, I would like to take this opportunity to thank you all for your patience, support and especially for all the feedback that […]
Well SALSA has just found a new center of interest. Using its semantic capabilities and some Google voodoo SALSA is able to quantify public information to your needs. A picture being worth a million (more?) dollars, here it is for you: Semantic Qualitative Evaluation.
It was not intended to use SALSA as a classification system. Many other tools exists that do a fair job. Yet as a side effect of mental semantic representation SALSA is capable of classifying unstructured-data by itself. Not only is this a nice feature but it’s computation is light. Meaning SALSA is a potential technology […]
During my daily idling/review of what is going on in the IT world, I came across the new challenge RPI is undertaking. Using IBM’s super computer “Blue Gene”, an artificial agent will attempt to pass the famous Turing test by October 2008.
While analyzing non-structured or dirty data it is sometimes hard to discriminate strings that are not actual words (garbage, tags, typos, …). In this case, the need of an automated method to differentiate actual words from garbage is of great help. While several approaches exist I will demonstrate two methods available at no cost with Open Source Software:
