Shallow parsers are usually assumed to be trained on {\it noise-free}
material, drawn from the same distribution as the testing
material. However, when either the training set is {\it noisy} or else
drawn from a {\it different} distributions, performance may be
degraded.  Using the parsed Wall Street Journal, we investigate the
performance of four shallow parsers (maximum entropy, memory-based
learning, N-grams and ensemble learning)  trained using various types
of artificially noisy material.  Our first set of results show that
shallow parsers are surprisingly robust to synthetic noise, with
performance gradually decreasing as the rate of noise increases.  Further
results show that no single shallow parser performs best in all noise
situations. Final results show that simple, parser-specific extensions
can improve noise-tolerance. Our second set of results addresses the
question of whether naturally occurring disfluencies undermines
performance more than does a change in distribution.  Results using
the parsed Switchboard corpus suggest that, although naturally
occurring disfluencies might harm performance, differences in
distribution between the training set and the testing set are more significant.
