Detecting Human Features in Summaries – Symbol Sequence Statistical Regularity

George Giannakopoulos¹, Vangelis Karkaletsis¹, and George A. Vouros²

¹Software and Knowledge Engineering Laboratory, National Center of Scientific Research “Demokritos”, Greece
[email protected]
[email protected]

²Department of Digital Systems, University of Pireaus, Greece
[email protected]

Abstract. The presented work studies textual summaries, aiming to detect the qualities of human multi-document summaries, in contrast to automatically extracted ones. The measured features are based on a generic statistical regularity measure, named Symbol Sequence Statistical Regularity (SSSR). The measure is calculated over both character and word n-grams of various ranks, given a set of human and automatically extracted multi-document summaries from two different corpora. The results of the experiments indicate that the proposed measure provides enough distinctive power to discriminate between the human and non-human summaries. The results hint on the qualities a human summary holds, increasing intuition related to how a good summary should be generated.

LNAI 7297, p. 114 ff.

Full article in PDF | BibTeX

[email protected]
© Springer-Verlag Berlin Heidelberg 2012