Human annotation of natural language facilitates standardized evaluation of natural language processing systems and supports automated feature extraction. This document consists of instructions for annotating the temporal information in scheduling dialogs, dialogs in which the participants schedule a meeting with one another. Task-oriented dialogs, such as these are, would arise in many useful applications, for instance, automated information providers and automated phone operators. Explicit instructions support good inter-rater reliability and serve as documentation for the classes being annotated.
@article{arxiv.cmp-lg/9702016,
title = {Instructions for Temporal Annotation of Scheduling Dialogs},
author = {Tom O'Hara and Janyce Wiebe and Karen Payne},
journal= {arXiv preprint arXiv:cmp-lg/9702016},
year = {2016}
}