Conclusion

Abstract

In this book was discussed the need to provide formal structures to contents originally created in unstructured formats using natural language. The volume of relevant information in such formats increases every day as people use the Internet to communicate, and as organizations create and publish documentation. The contents are often without formalized markups because marking contents manually can be a time consuming and error prone task that requires some specialized knowledge. The objective of information extraction is to analyze these contents and produce fixed format, unambiguous and formal representations of them, including the identification of the entities involved and the relations they establish among them.