Title Summarization of Multimodal Information
Author(s) Saif Ahmad, Paulo C F de Oliveira, Khurshid Ahmad

Department of Computing, University of Surrey, Guildford, Surrey, UK

Session O29-EMSW
Abstract Information Summarization is one of the key challenges for current and future information systems. In this paper, we will outline a system that comprises modules for summarizing texts and time series to study the link between the two. Summaries of texts are generated using a lexical analysis of cohesion in texts focusing on key sentences that provide cohesion: by implication, these are the sentences that comprise chief points of a given text. Time series summarization is accomplished using the so-called wavelet analysis to separate out the trend, cyclical fluctuations and autocorrelational effects and generating verbal signals to describe each phenomenon. Finally, we present a case study performed on the UK financial market with regards to multimodal information processing, namely textual and numerical summarization.
Keyword(s) Summarization, time series analysis, summary evaluation, lexical cohesion, and wavelets
Language(s) English
Full Paper 502.pdf