Development of a data-to-text (D2T) system to generate news on streaming data

Ahmad Zainal Abidin, Enjang Ali Nurdin, Lala Septem Riza

Abstract


This research aims to develop a Data-to-Text system with input in the form of streaming data in batch form, to generate news in general. The development of a Data-to-Text system model is carried out by applying Machine Learning to overcome Streaming data, with the Piecewise Linear Approximation technique using the Least Square method. The developed system produces data summary information, current data information, and prediction information. System development is carried out in the R programming language by utilizing several available packages. The experiment was conducted by measuring the Readability level of the news raised, Computation Time, and comparing the results with
related research. The experimental results show that the information produced is proven to represent the data provided and can be understood by the student level or above, and the computational time is quite good. The system can generate information based on meteorological data, climatological data, and financial data.


Keywords


Data-to-text; least square method; machine learning;natural language generation;picewise linear approximation;streaming;time-series.

Full Text:

PDF

References


Barros, C., Lloret, E., Saquete, E., and Navarro-Colorado, B. (2019). NATSUM: Narrative abstractive summarization through cross-document timeline generation. Information Processing and Management, 56(5), 1775-1793.

Barros, C., Vicente, M., and Lloret, E. (2021). To what extent does content selection affect surface realization in the context of headline generation?. Computer Speech and Language, 67, 101179.

García-Méndez, S., Fernández-Gavilanes, M., Costa-Montenegro, E., Juncal-Martínez, J., González-Castaño, F. J., and Reiter, E. (2019). A system for automatic English text expansion. IEEE Access, 7, 123320-123333.

Gkatzia, D., Lemon, O., and Rieser, V. Information to-text age further develops dynamic under vulnerability. IEEE Computational Intelligence Magazine, 12(3), 10-17.

Kittredge, R. I. and Driedger, N. (1994). Utilizing normal language handling to create weather conditions estimates. IEEE Master. Syst. their Appl., 9(2), 45-53.

Kondadadi, R., Howald, B., and Schilder, F. (2013, August). A statistical NLG framework for aggregated planning and realization. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics 1(Long Papers), 1406-1415.

Muthukrishnan, S. Information streams: Calculations and applications. Computer Science, 1(2), 117-236.

Ramos-Soto, A., Bugarín, A., and Barro, S. On the job of phonetic depictions of information in the structure of normal language age frameworks. Fluffy Sets Syst., 285, 31-51.

Reiter, E. (2011). A Design for information to-text frameworks. Computational Intelligence, 27(1), 23-40.

S. Ramos, R. M., Monteiro, D. S., and Paraboni, I. (2020). Personality-dependent content selection in natural language generation systems. Journal of the Brazilian Computer Society, 26(1), 2.

van der Lee, C., Gatt, A., van Miltenburg, E., and Krahmer, E. (2021). Human evaluation of automatically generated text: Current trends and best practice guidelines. Computer Speech and Language, 67, 101151.

Vayre, J. S., Delpech, E., Dufresne, A., and Lemercier, C. (2017). Communication mediated through natural language generation in big data environments: the case of Nomao. Journal of Computer and Communications, 5(6), 125-148.

Vicente, M., Barros, C., and Lloret, E. (2018). Statistical language modelling for automatic story generation. Journal of Intelligent and Fuzzy Systems, 34(5), 3069-3079.

Yagamurthy, D. N., Azmeera, R., and Khanna, R. (2023). Natural Language Generation (NLG) for Automated Report Generation. Journal of Technology and Systems, 5(1), 48-59.

Zubair, F., and Jafir, A. (2021). Natural Language Generation: Recent Advances and Applications. International Journal of Advanced Engineering Technologies and Innovations, 1(1), 50-74.




DOI: https://doi.org/10.17509/jcs.v5i2.70799

Refbacks

  • There are currently no refbacks.