A semantic framework for meeting data retrieval

  • Authors:
  • Weisheng He;Peifeng Xiang;Yuanchun Shi

  • Affiliations:
  • Tsinghua University, Beijing, RPC;Tsinghua University, Beijing, RPC;Tsinghua University, Beijing, RPC

  • Venue:
  • CARPE '05 Proceedings of the 2nd ACM workshop on Continuous archival and retrieval of personal experiences
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Meetings are often captured for future access in daily life and with an increasing amount of such record, computers should be used to process and retrieve the meeting content to improve the access efficiency. This requires a semantic framework to formally represent and model the meeting procedure and user intentions so that they can be processed by machines. In this paper, we present a framework, MiF (Meeting information Framework), to structurally formalize meeting contents and user retrieval queries. MiF consists of four components: the primitive ontology provides the schema to define basic semantic units and their interrelation; the archive expression model (AEM) enables a comprehensive representation of the meeting procedure; the query expression model (QEM) supports the formalization of high-level, semantic-rich retrieval queries; the query processor executes queries and makes necessary inference based on the primitive ontology. With this framework, a prototype system for meeting record has been implemented, by which hypermedia data can be automatically captured and complex user queries can be expressed and processed for an efficient retrieval.