Skip to main content
SpringerLink
Log in

LSTM-based Siamese neural network for Urdu news story segmentation

  • Special Issue Paper
  • Published:
International Journal on Document Analysis and Recognition (IJDAR) Aims and scope Submit manuscript

Abstract

News story segmentation is a challenging task mainly due to the dynamic range of topics, smooth story transitions, and varied duration of each story. This paper presents a technique to segment stories from Urdu news bulletins. The technique relies on a Long Short-Term Memory-based Siamese neural network that is trained on positive (belonging to the same story) and negative (belonging to different stories) pairs of sentences. The model, once trained, identifies the transition between stories by detecting the dissimilarity between the adjacent sentences of a given text. For algorithmic development and experimental study, we employ two datasets, a dataset of Urdu news as well as transcriptions of news bulletins from multiple news channels. Experiments report promising results in identifying story boundaries validating the ideas put forward in this study.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Ahlers, D.: News consumption and the new electronic media. Harv. Int. J. Press-Polit. 11, 29–52 (2006). https://doi.org/10.1177/1081180X05284317

    Article  Google Scholar 

  2. Ahmad, R., Afzal, MZ., Rashid, SF., et al.: Space anomalies in ocrs for arabic like scripts. In: 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), IEEE, pp 67–71 (2018)

  3. Ahmed, S.B., Naz, S., Swati, S., et al.: Ucom offline dataset-an urdu handwritten dataset generation. Int. Arab J. Inf. Technol. 14, 239–245 (2017)

    Google Scholar 

  4. Bromley, J., Guyon, I., LeCun, Y., et al.: Signature verification using a" siamese" time delay neural network. Adv. Neural Inf. Process. Syst. 6 (1993)

  5. Chaisorn, L., Chua, TS., Koh, CK., et al.: A two-level multi-modal approach for story segmentation of large news video corpus. In: TRECVID (2003)

  6. Chen, H., Wang, Z., Pei, Y., et al.: Story segmentation for news broadcast based on primary caption. In: Proceedings of the 2nd ACM International Conference on Multimedia in Asia. Association for Computing Machinery, New York, NY, USA, MMAsia ’20, 10.1145/3444685.3446298, (2021) https://doi.org/10.1145/3444685.3446298

  7. Chi, Z., Zhang, B.: A sentence similarity estimation method based on improved siamese network. J. Intell. Learn. Syst. Appl. 10(4), 121–134 (2018)

    MathSciNet  Google Scholar 

  8. Chua, T.S., Chang, S.F., Chaisorn, L., et al.: Story boundary detection in large broadcast news video archives: techniques, experience and trends. In: MULTIMEDIA ’04 (2004)

  9. Dey, S., Dutta, A., Toledo, J.I., et al.: Signet: Convolutional siamese network for writer independent offline signature verification. (2017) arXiv preprint arXiv:1707.02131

  10. Farooq, M.U., Adeeba, F., Rauf, S., et al.: Improving large vocabulary urdu speech recognition system using deep neural networks. In: INTERSPEECH, pp 2978–2982 (2019)

  11. Feng, B., Chen, Z., Zheng, R., et al.: Multiple style exploration for story unit segmentation of broadcast news video. Multimed. Syst. 20(4), 347–361 (2014)

    Article  Google Scholar 

  12. Fiscus, J.G., Doddington, G.R.: Topic detection and tracking evaluation overview. In: Topic Detection and Tracking. Springer, p 17–31 (2002)

  13. Haloi, P., Bhuyan, M., Chatterjee, D., et al.: Unsupervised story segmentation and indexing of broadcast news video. Multimedia Tools and Applications pp 1–20 (2021)

  14. Hashimoto, I., Wang, Y., Kawai, Y., et al.: Topic detection for video stream based on geographical relationships and its interactive viewing system. In: 2021 IEEE 4th International Conference on Multimedia Information Processing and Retrieval (MIPR), IEEE, pp 28–34 (2021)

  15. Hauptmann, A., Witbrock, M.: Story segmentation and detection of commercials in broadcast news video. In: Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL’98-, pp 168–179, 10.1109/ADL.1998.670392 (1998)

  16. Hussain, K., Mughal, N., Ali, I., et al.: Urdu news dataset 1m. Mendeley Data 3 (2021)

  17. Kannao, R., Guha, P.: Story segmentation in tv news broadcast. In: 2016 23rd International Conference on Pattern Recognition (ICPR), IEEE, pp 2948–2953 (2016)

  18. Kannao, R., Guha, P.: Segmenting with style: detecting program and story boundaries in tv news broadcast videos. Multimed. Tools Appl. 78(22), 31925–31957 (2019)

    Article  Google Scholar 

  19. Kechaou, Z., Wali, A., Ben Ammar, M., Karray, H., Alimi, A.M.: A novel system for video news’ sentiment analysis. J. Syst. Inf. Technol. 15(1), 24–44 (2013)

    Article  Google Scholar 

  20. Këpuska, V., Bohouta, G.: Comparing speech recognition systems (microsoft api, google api and cmu sphinx). Int. J. Eng. Res. Appl. 7(03), 20–24 (2017)

    Google Scholar 

  21. Khan, N.H., Adnan, A.: Urdu optical character recognition systems: present contributions and future directions. IEEE Access 6, 46019–46046 (2018)

    Article  Google Scholar 

  22. Kumar, M., Jindal, M.K., Sharma, R.K., et al.: Character and numeral recognition for non-indic and indic scripts: a survey. Artif. Intell. Rev. 52, 2235–2261 (2019)

    Article  Google Scholar 

  23. Kumar, V., Sundaram, S.: Siamese based neural network for offline writer identification on word level data. (2022) arXiv preprint arXiv:2211.14443

  24. Liu, Z., Wang, Y.: Tv news story segmentation using deep neural network. pp 1–4 (2018)

  25. Lu, X., Leung, C.C., Xie, L., et al.: Broadcast news story segmentation using latent topics on data manifold. In: 2013 IEEE International Conference on Acoustics, pp. 8465–8469. Speech and Signal Processing, IEEE (2013)

    Google Scholar 

  26. Mansouri, S., Charhad, M., Rekik, A., et al.: A framework for semantic video content indexing using textual information. In: 2018 IEEE second international conference on data stream mining & processing (DSMP), IEEE, pp 107–110 (2018)

  27. Mirza, A., Siddiqi, I.: Recognition of cursive video text using a deep learning framework. IET Image Proc. 14(14), 3444–3455 (2020)

    Article  Google Scholar 

  28. Mirza, A., Zeshan, O., Atif, M., et al.: (2020) Detection and recognition of cursive text from video frames. EURASIP J. Image Video Process. 1, 1–19 (2020)

    Google Scholar 

  29. Misra, H., Hopfgartner, F., Goyal, A., et al.: Tv news story segmentation based on semantic coherence and content similarity. In: International Conference on Multimedia Modeling, Springer, pp 347–357 (2010)

  30. Mushtaq, F., Misgar, M.M., Kumar, M., et al.: Urdudeepnet: offline handwritten Urdu character recognition using deep neural network. Neural Comput. Appl. 33(22), 15229–15252 (2021)

    Article  Google Scholar 

  31. Ruiz, V., Linares, I., Sanchez, A., et al.: Off-line handwritten signature verification using compositional synthetic generation of signatures and siamese neural networks. Neurocomputing 374, 30–41 (2020)

    Article  Google Scholar 

  32. Saedi, C., Dras, M.: Siamese networks for large-scale author identification. Comput. Speech Lang. 70(101), 241 (2021)

  33. Smeaton, A., Over, P.: Trecvid 2006: Shot boundary detection task overview. In: Proceedings of the TRECVID Workshop (2006)

  34. Spolaor, N., Lee, H.D., Takaki, W.S.R., et al.: A systematic review on content-based video retrieval. Eng. Appl. Artif. Intell. 90(103), 557 (2020)

    Google Scholar 

  35. Urala Kota, B., Davila, K., Stone, A., et al.: Generalized framework for summarization of fixed-camera lecture videos by detecting and binarizing handwritten content. Int. J. Doc. Anal. Recognit. 22(3), 221–233 (2019)

    Article  Google Scholar 

  36. Vinciarelli, A., Favre, S.: Broadcast news story segmentation using social network analysis and hidden markov models. In: Proceedings of the 15th ACM International Conference on Multimedia. Association for Computing Machinery, New York, NY, USA, MM ’07, p 261-264 (2007)

  37. Wang, Y., Yao, Q., Kwok, J.T., et al.: Generalizing from a few examples: a survey on few-shot learning. ACM Comput. Surv. 53(3), 1–34 (2020)

    Article  Google Scholar 

  38. Xie, L., Yang, Y.L., Liu, Z.Q.: On the effectiveness of subwords for lexical cohesion based story segmentation of chinese broadcast news. Inf. Sci. 181(13), 2873–2891 (2011)

    Article  Google Scholar 

  39. Yasin, D., Sohail, A., Siddiqi, I.: Semantic video retrieval using deep learning techniques. In: 2020 17th International Bhurban Conference on Applied Sciences and Technology (IBCAST), IEEE, pp 338–343 (2020)

  40. Yu, J., Shao, H.: Broadcast news story segmentation using sticky hierarchical dirichlet process. Appl. Intell. 52(11), 12788–12800 (2022)

    Article  Google Scholar 

  41. Yu, J., Xie, L., Xiao, X., et al.: A hybrid neural network hidden markov model approach for automatic story segmentation. J. Ambient. Intell. Humaniz. Comput. 8(6), 925–936 (2017)

    Article  Google Scholar 

  42. Zhou, M., Fan, Z., Wang, R., et al.: News video story segmentation with multi-modality features. In: 2020 8th International Conference on Digital Home (ICDH), pp 271–275 (2020)

Download references

Author information

Author notes

  1. Imran Siddiqi and Momina Moetesum have equally contributed to this work.

Authors and Affiliations

  1. Department of Computer Science, Bahria University, Islamabad, Pakistan

    Muhammad Nauman Ahmed Bhatti

  2. Landmark Resources Pvt. Ltd., Islamabad, Pakistan

    Muhammad Nauman Ahmed Bhatti

  3. Center of Excellence in Artificial Intelligence, Bahria University, Islamabad, Pakistan

    Imran Siddiqi

  4. Xynoptik Pty Ltd., Melbourne, Australia

    Imran Siddiqi

  5. School of Electrical Engineering and Computer Science, National University of Science and Technology, Islamabad, Pakistan

    Momina Moetesum

Authors
  1. Muhammad Nauman Ahmed Bhatti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Imran Siddiqi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Momina Moetesum
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed equally to the preparation of the manuscript from idea conceptualization to experimentation and write-up.

Corresponding author

Correspondence to Momina Moetesum.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bhatti, M.N.A., Siddiqi, I. & Moetesum, M. LSTM-based Siamese neural network for Urdu news story segmentation. IJDAR 26, 363–373 (2023). https://doi.org/10.1007/s10032-023-00441-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10032-023-00441-y

Keywords

Search

Navigation