Skip to main content
Log in

News story segmentation in multiple modalities

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this paper, we describe an approach to segmenting news video based on the perceived shift in content using features spanning multiple modalities. We investigate a number of multimedia features, which serve as potential indicators of a change in story, in order to determine which are the most effective. The efficacy of our approach is demonstrated by the performance of our prototype, where a number of feature combinations demonstrate an up to 18% improvement in WindowDiff score compared to other state of the art story segmenters. In our investigation, there is no, one, clearly superior feature, rather the best segmentation occurs when there is synergy between multiple features. A further investigation into the effect on segmentation performance, while varying the number of training examples versus the number of features used, reveal that having better feature combinations is more important than having more training examples. Our work suggests that it is possible to train robust story segmenters for news video using only a handful of broadcasts, provided a good initial feature selection is made.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Notes

  1. http://www-nlpir.nist.gov/projects/tv2004/tv2004.html

  2. This function invokes the maximum entropy classifier, which trains a model (maxentModel) based on the provided positive (positiveFeatures) and negative (negativeFeatures) examples. We used the OpenNLP Maxent library: http://maxent.sourceforge.net

References

  1. Amir A, Argillander J, Berg M, Chang S-F, et al. (2004) “IBM research TRECVID-2004 video retrieval system.” Proceedings of TRECVID.

  2. Beeferman D, Berger A, Lafferty J (1999) Statistical models for text segmentation. Mach Learn 34(1):177–210

    Article  MATH  Google Scholar 

  3. Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet Allocation. Journal of Machine Learning Research 3:993–1022

    Article  MATH  Google Scholar 

  4. Choi F (2000) “Advances in domain independent linear text segmentation.” Proceedings of North American Chapter of the Association for Computational Linguistic.

  5. Dekens T, Demol M, Verhelst W, Beaugendre F (2007) “Voice activity detection based on inverse normalized noise likelihood estimation.” Proceedings of Convention of Electrical Engineering 2007, Santa Clara, Cuba, June 18–22.

  6. Ferret O (2002) “Using collocations for topic segmentation and link detection.” Conference on Computational Linguistics.

  7. Finkel J, Grenager T, Manning C (2005) “Incorporating non-local information into information extraction systems by Gibbs sampling.” Proceedings of Association for Computational Linguistic.

  8. Foltz P, Kintsch W, Landauer T (1998) The measurement of textual coherence with latent semantic analysis. Discourse Processes 25:285–307

    Article  Google Scholar 

  9. Galley M, McKeown K, Fosler-Lussier E, Jing H (2003) “Discourse segmentation of multi-party conversation.” Proceedings of Association for Computational Linguistics, Sapporo, Japan, 562–569.

  10. Hearst MA (1997) TextTiling: segmenting text into multi-paragraph subtopic passages. Comput Linguist 23(1):33–64

    Google Scholar 

  11. Hirschberg J, Litman D (1993) Empirical studies on the disambiguation of cue phrases. Comput Linguist 19(3):501–530

    Google Scholar 

  12. Kan M-Y, Klavans JL, McKeown KR (1998) “Linear segmentation and segment significance.” Proc. 6th Workshop on Very Large Corpora.

  13. Kozima H (1993) “Text segmentation based on similarity between words.” Proceedings of Association for Computational Linguistics: 286–288.

  14. Nakamura Y, Kanade T (1997) “Semantic analysis for video contents extraction — spotting by association in news video.” ACM Multimedia: 393–401.

  15. Olney A, Cai Z (2005) “An orthonormal basis for topic segmentation in tutorial dialogue.” Procedings of Human Language Technology Conference/Conference on Empirical Methods in Natural Language Processing.

  16. Osian M, Van Gool L (2004) Video shot characterization. Mach Vis Appl 15(3):172–177

    Article  Google Scholar 

  17. Passonneau RJ, Litman DJ (1993) “Intention-based segmentation: Human reliability and correlation with linguistic cues.” Proceedings of Association for Computational Linguistics, 148–155.

  18. Pevzner L, Hearst M (2002) A critique and improvement of an evaluation metric for text segmentation. Comput Linguist 28(1):19–36

    Article  Google Scholar 

  19. Ponte JM, Croft WB (1997)“Text segmentation by topic.” European Conference on Digital Libraries, 113–125.

  20. Quenot G, Moraru D, Ayache S, Charhad M, Guironnet M, Carminati L, Mulhem P, Gensel J, Pellerin D, Besacier L (2004)“CLIPS-LIS-LSR-LABRI experiments at TRECVID.” Proceedings of TRECVID 2004.

  21. Stokes N, Carthy J, Smeaton A (2004) SeLeCT: a lexical cohesion based news story segmentation system. AI Commun 17(1):3–12

    MATH  MathSciNet  Google Scholar 

  22. Tur G, Hakkani-Tüur D, Stolcke A, Shriberg E (2001) Integrating prosodic and lexical cues for automatic topic segmentation. Comput Linguist 27(1):31–57

    Article  Google Scholar 

Download references

Acknowledgments

The work reported is supported by the EU-IST project CLASS (Cognitive-Level Annotation using Latent Statistical Structure, IST-027978) and by the IWT-SBO project AMASS++ (Advanced Multimedia Alignment and Structured Summarization, IWT 060051).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Gert-Jan Poulisse.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Poulisse, GJ., Moens, MF., Dekens, T. et al. News story segmentation in multiple modalities. Multimed Tools Appl 48, 3–22 (2010). https://doi.org/10.1007/s11042-009-0358-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-009-0358-9

Keywords

Navigation