Unformatted text preview: where we know in
advance what kind of semantic information we are looking for. The main task
is to extract parts of text and assign speciﬁc attributes to it.
As an example consider the task to extract executive position changes from
news stories: "Robert L. James, chairman and chief executive ofﬁcer of McCannErickson, is going to retire on July 1st. He will be replaced by John J. Donner, Jr.,
the agencies chief operating ofﬁcer." In this case we have to identify the following
information: Organization (McCann-Erickson), position (chief executive ofﬁcer),
date (July 1), outgoing person name (Robert L. James), and incoming person
name (John J. Donner, Jr.).
The task of information extraction naturally decomposes into a series of
processing steps, typically including tokenization, sentence segmentation, part- Band 20 – 2005 45 Hotho, Nürnberger, and Paaß
of-speech assignment, and the identiﬁcation of named entities, i.e. person
names, location names and names of organizations....
View Full Document