Theme:Anaphora resolution applied to spoken discourse
Procedure:
Select a one-page section of the naturally occuring spoken discourse
you collected for Assigment #1. Select one of the anaphora resolution
algorithms discussed in class: RAP (Lappin & Leass 1994), Centering (Brennan
et al 1987), or CogNIAC (Baldwin 1995). For each utterance in your
section, describe the actions taken by your chosen resolution procedure
on that utterance. You should record the updates made to the discourse
structures as each utterance is processed: e.g. list the Cf, Cp, and Cb for
Centering, and what each anaphor in the utterance would resolve to.
Discussion:
The algorithms discussed in class had about an 80% accuracy rate
on monologue texts. How do they perform on your more naturalistic discourses?
How do they do when modeling multi-party discourse rather than monologues?
What types of anaphora in your discourse were most problematic? easiest?
Most of the examples worked through in class and in the text were a
few sentences long. Were there any difficulties that you would associate
with the longer discourses, e.g. changes in topics?
We ask you to turn in the printed hand-simulation of the anaphora
resolution algorithm as applied to one page of your transcribed discourse
and a discussion of the points listed above.