An Empirical Approach to Temporal Reference Resolution (journal version)

TL;DR

This paper presents an empirical investigation into resolving explicit temporal references in scheduling dialogs, developing and evaluating a system based on a recency-focused model across diverse datasets.

Contribution

It introduces a reliable annotation process, develops a fully automatic system, and evaluates the effectiveness of a recency-based focus model for temporal reference resolution.

Findings

High annotation reliability among naive annotators

System performs well on unseen data sets

Recency-based focus model has low ambiguity and few errors

Abstract

Scheduling dialogs, during which people negotiate the times of appointments, are common in everyday life. This paper reports the results of an in-depth empirical investigation of resolving explicit temporal references in scheduling dialogs. There are four phases of this work: data annotation and evaluation, model development, system implementation and evaluation, and model evaluation and analysis. The system and model 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 approach. Detailed annotation instructions were developed and an intercoder reliability study was performed, showing that naive annotators can reliably perform the targeted annotations. A fully automatic system has been developed and evaluated on unseen test data, with good results on both data sets. We adopt a pure realization of a recency-based focus model to identify precisely when it is and is not adequate for the task being addressed. In addition to system results, an in-depth evaluation of the model itself is presented, based on detailed manual annotations. 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.