In the last session we focused on Natural Language Processing, which is an integral part of all semantic
technologies. In this session, we begin to look at the types of things that Natural Language Processing allows us to do. A lot of what we will be describing here falls under the general label of Text Analysis or Text Mining. This session focuses on the simplest and most basic form of text analysis, pure word extraction.
Pure word extraction is not as sophisticated as grammatical or concept based extraction, which we will
be looking at in the next two sessions, so there are not as many applications we can build with our
results. However, our approach throughout this course continues to be starting at a basic level
and increasing in complexity as we go along.
This week’s assignment on Pure Word Extraction is similar to last week’s on Natural Language Processing
in that we are again looking at a tool which is unlikely to provide a great deal of value on its own, in terms of Knowledge Processing, but is likely to be a critical component of any tool which we do design or use.