AN EMPIRICAL-APPROACH TO TEMPORAL REFERENCE RESOLUTION

Scheduling dialogs, during which people negotiate the times of appoint ments, are common in everyday life. This paper reports the results of an in-depth empirical investigation of resolving explicit temporal ref erences in scheduling dialogs. There are four phases of this work: dat a annotation and evaluation, model development, system implementation and evaluation, and model evaluation and analysis. The system and mode l were developed primarily on one set of data, and then applied later to a much more complex data set, to assess the generalizability of the model for the task being performed. Many different types of empirical methods are applied to pinpoint the strengths and weaknesses of the a pproach. Detailed annotation instructions were developed and an interc oder reliability study was performed, showing that naive annotators ca n reliably perform the targeted annotations. A fully automatic system has been developed and evaluated on unseen test data, with good result s on both data sets. We adopt a pure realization of a recency-based fo cus model to identify precisely when it is and is not adequate for the task being addressed. In addition to system results, an in-depth eval uation of the model itself is presented, based on detailed manual anno tations. The results are that few errors occur specifically due to the model of focus being used, and the set of anaphoric relations defined in the model are low in ambiguity for both data sets.