An approach to solving the problem of automatic briefing generation from non-textual events can be segmenting the task into two
major steps, namely, extraction of briefing templates and learning aggregators that collate information from events and automatically fill up the templates. In this paper, we describe two novel unsupervised approaches for extracting briefing templates from human written reports. Since the problem is non-standard, we define our own criteria for evaluating the approaches and demonstrate that both approaches are effective in extracting domain relevant templates with promising accuracies.

Powered by liveSite