Abstract
An important problem with mining textual information is that in this unstructured form is not readily accessible to be used by computers. This has been written for human readers and requires, when feasible, some natural language interpretation. Although full processing is still out of reach with current technology, there are tools using basic pattern recognition techniques and heuristics that are capable of extracting valuable information from free text based on the elements contained in it (i.e., keywords). This technology is usually referred to as Text Mining, and aims at discovering unseen and interesting patterns in textual databases [8], [19].
Original language | English |
---|---|
Title of host publication | Natural Language Processing and Text Mining |
Publisher | Springer London |
Pages | 145-169 |
Number of pages | 25 |
ISBN (Print) | 184628175X, 9781846281754 |
DOIs | |
State | Published - 2007 |
Externally published | Yes |