There is almost no end to the sorts of analyses you can do with text. This diagram and article offer a fascinating exploration of the choices you can make, and of the many applications (often open source!) than can be used in text analysis. The lesson to be drawn from this is that it's possible for almost anyone - and not just IBM or Google - to do basic text analytics. Approaching text from the perspective of standard frameworks makes it possible to link them together. "One advantage of using toolkits is that they make it easy to pass the output from one NLP component to another. However, sometimes, you need to combine components from different libraries. UIMA and GATE both mitigate this problem by offering frameworks, which can combine components from different authors, some of which can be open-source and others commercial, into a single systems."
Today: 7 Total: 46 [Direct link] [Share]
View full size
