Paper: Generating Natural Language Summaries for Multimedia

ACL ID W12-1522
Title Generating Natural Language Summaries for Multimedia
Venue International Conference on Natural Language Generation
Session Main Conference
Year 2012
Authors

Generating Natural Language Summaries for Multimedia Duo Ding, Florian Metze, Shourabh Rawat, Peter F. Schulam, Susanne Burger School of Computer Science, Carnegie Mellon University Pittsburgh, PA, USA 15213 {dding, fmetze, srawat, pschulam, sburger}@cs.cmu.edu Abstract In this paper we introduce an automatic sys-tem that generates textual summaries of Inter-net-style video clips by first identifying suitable high-level descriptive features that have been detected in the video (e.g. visual concepts, recognized speech, actions, objects, persons, etc.). Then a natural language genera-tor is constructed using SimpleNLG to com-pile the high-level features into a textual form. The generated summary contains information from both visual and acoustic sources, intend-ing to give a general rev...