dage, and Connell 1998). These qualifiers could be
temporal (for example, “pain started two days ago”),
spatial (“pain in the epigastric region”), or other asso-
ciations (“pain after eating fatty foods”). Implicit in
this task is the human’s ability to extract concepts
and their associated qualifiers from the natural lan-
guage narrative. For example, the above qualifiers
might have to be extracted from the sentence “The
patient reports pain, which started two days ago, in
the epigastric region especially after eating fatty
The computer system needs to perform a similar
analysis of the narrative. We use the term factor to
denote the potentially relevant observations along
Figure 3. Visualization of an Assertion Graph.
By convention, input factors are placed at the top and hypotheses at the bottom with levels of inference factors in between.
A 63-year-old patient
is sent to the
neurologist with ...
resting tremor ... What
part of his nervous
system is most likely
An edge represents a relation
between the connected
statements. Agents make
assertions about the truth of
these relations with
con;dences. Edge width
represents that con;dence.
Gray level represents the
amount of belief ;ow.
A node represents a statement.
Types of statements are input
factors, inferred factors and
hypotheses or answers. Border
strength visually represents
“belief” the factor is true in