A natural language model for managing TV-Anytime information in mobile environments

• Published in: Personal and ubiquitous computing Vol. 9; no. 5; pp. 262 - 272
• Main Authors: Karanastasi, Anastasia, Kazasis, Fotis G., Christodoulakis, Stavros
• Format: Journal Article
• Language: English
• Published: London Springer Nature B.V 01.09.2005
• Subjects: Metadata; Mobile communications networks; Television programs
• ISSN: 1617-4909; 1617-4917
• DOI: 10.1007/s00779-004-0330-7

The TV-Anytime standard describes the structures of categories of digital TV program metadata, as well as user prole metadata for TV programs. We describe a natural language (NL) model for the users to interact with the TV-Anytime metadata and preview TV programs from their mobile devices. The language utilises completely the TV-Anytime metadata specications (upper ontologies), as well as domain-specic ontologies. The interaction model does not use clarication dialogues, but it uses the user proles as well as TV-Anytime metadata information and ontologies to rank the possible responses in case of ambiguities. We describe implementations of the model that run on a PDA and on a mobile phone, and manage the metadata on a remote TV-Anytime-compatible TV set. We present user evaluations of the approach. Finally, we propose a generalised implementation framework that can be used to easily provide NL interfaces for mobile devices for different applications and ontologies. [PUBLICATION ABSTRACT]