Abstract
This paper explores dierent methods for interpreting the results of
multiple, cascad- ing machine learners, each of which per- forms a
dierent task. For instance, the rst learner may classify news as
\sports," the second learner may extract the people from the sports
articles, and the third learner may classify the extracted people as
belonging to a certain team. We present a framework for modeling such
cascading learners as a di- rected acyclic graph, which allows us to
con- struct three-way contingency tables on which we can perform
various independence tests. These independence tests provide insight
into how the various learners' performance de- pend on their
predecessor in the chain and/or the inputs themselves.