Coding Dialogs with the DAMSL Annotation Scheme

This paper describes the DAMSL annotation scheme
for communicative acts in dialog. The scheme has
three layers: Forward Communicative Functions,
Backward Communicative Functions, and Utterance
Features. Each layer allows multiple communicative
functions of an utterance to be labeled. The Forward
Communicative Functions consist of a taxonomy in
a similar style as the actions of traditional speech act
theory. The Backward Communicative Functions indicate how the current utterance relates to the previous
dialog, such as accepting a proposal, confirming understanding, or answering a question. The Utterance Features include information about an utterance's form
and content, such as whether an utterance concerns
the communication process itself or deals with the
subject at hand. The kappa inter-annotator reliability
scores for the first test of DAMSL with human annotators show promise, but are on average 0.15 lower than
the accepted kappa scores for such annotations. However, the slight revisions to DAMSL discussed here
should increase accuracy on the next set of tests and
produce a reliable, flexible, and comprehensive utterance annotation scheme.