Ideally a computational approach could assist in the human-intensive tasks
associated with selecting and presenting timely, relevant information, i.e.
, news editing. At present this goal is difficult to achieve because of the
paucity of effective machine-understanding systems for news. A structure f
or news that affords a fluid interchange between human and machine-derived
expertise is a step toward improving both the efficiency and utility of on-
line news. This paper examines a system that employs richer representations
of texts within a corpus of news. These representations are composed by a
collection of experts who examine news articles in the database, looking at
both the text itself and the annotations placed by other experts. These ex
perts employ a variety of methods ranging from statistical examination to n
atural-language parsing to query expansion through specific-purpose knowled
ge bases. The system provides a structure for the sharing of knowledge with
human editors and the development of a class of applications that make use
of article augmentation.