Implementasi Pencarian Link graph terbaik dalam menentukan Kalimat Representatif Pada Peringkasan Dokumen Berbahasa Indonesia

Irwan Darmawan(1*), Sholeh Rachmatullah(2), Nilam Ramadhani(3),

(1) Universitas Madura, Pamekasan, Indonesia
(2) Universitas Madura, Pamekasan, Indonesia
(3) Universitas Madura, Pamekasan, Indonesia
(*) Corresponding Author

Abstract


Indonesian documents have many or several sentences that are considered important in summarizing one document or many documents, sentences that appear a lot in documents are usually considered important sentences or reflect representative sentences on a document, even though these are not necessarily sentences that should be taken and put into representative sentences in determining the summarization of documents. In the link graph method used, it can indeed determine the amount of sentence weight in each sentence, it becomes a problem when sentence cutting is done if it is considered to have a very small weight. So a solution is needed to overcome this, namely by finding or determining the best parameters on the link graph of each sentence in the document summary. The value of such parameters is used to determine the truncation of each sentence. If the weight value of the sentence does not reach the limit of the parameter to be searched then the sentence is not included in the sentence processing in determining the summary of the document. The test parameters used are lambda i.e. (0.1, 0.3, 0.5) and for dumping factor i.e. (0.3, 0.5, 0.8)

Full Text:

PDF

References


C. Kwatra and K. Gupta, “Extractive and Abstractive Summarization for Hindi Text using Hierarchical Clustering,” Proc. 2021 IEEE Int. Conf. Innov. Comput. Intell. Commun. Smart Electr. Syst. ICSES 2021, 2021, doi: 10.1109/ICSES52305.2021.9633789.

J. Asian, “Effective Techniques for Indonesian Text Retrieval,” Ph.D Thesis, pp. 1–286, 2007, [Online]. Available: https://researchrepository.rmit.edu.au/esploro/outputs/doctoral/Effective-techniques-for-Indonesian-text-retrieval/9921861570701341

S. Singh and A. Mahmood, “The NLP Cookbook: Modern Recipes for Transformer Based Deep Learning Architectures,” IEEE Access, vol. 9, pp. 68675–68702, 2021, doi: 10.1109/ACCESS.2021.3077350.

J. Asian, H. E. Williams, and S. M. M. Tahaghoghi, “Stemming Indonesian,” Conf. Res. Pract. Inf. Technol. Ser., vol. 38, no. September 2018, pp. 307–314, 2005, doi: 10.1145/1316457.1316459.

I. Darmawan and N. Haidar Hari, “Discourse Connectors Pada Peringkasan Dokumen Berbahasa Indonesia,” SMARTICS J., vol. 7, no. 1, pp. 33–41, 2021, [Online]. Available: https://doi.org/10.21067/smartics.v7i1.5046

I. Darmawan, R. A. H, and H. Armato, “InfoTekJar : Jurnal Nasional Peringkasan paper dengan metode Sparse Nonnegative Matrix Factorization untuk Pemeriksaan Kesesuaian dengan Abstrak Tugas Akhir,” vol. 1, 2020.

N. Ramadhani, “View of Penerapan Algoritma Naïve Bayes Classifier dan Fungsi Gaussian Untuk Penentuan Penjurusan Siswa Kelas X.pdf,” vol. 8, no. 1, pp. 14–21, 2022.

M. Asfi and N. Fitrianingsih, “Implementasi Algoritma Naive Bayes Classifier sebagai Sistem Rekomendasi Pembimbing Skripsi,” InfoTekJar J. Nas. Inform. dan Teknol. Jar., vol. 5, no. 1, p. 44, 2020.

A. El-Kilany and I. Saleh, “Unsupervised document summarization using clusters of dependency graph nodes,” Int. Conf. Intell. Syst. Des. Appl. ISDA, pp. 557–561, 2012, doi: 10.1109/ISDA.2012.6416598.

H. Zheng and M. Lapata, “Sentence centrality revisited for unsupervised summarization,” ACL 2019 - 57th Annu. Meet. Assoc. Comput. Linguist. Proc. Conf., no. 2, pp. 6236–6247, 2020, doi: 10.18653/v1/p19-1628.

A. Alifimoff, “Abstractive Sentence Summarization with,” pp. 1–9.

Y. C. Tseng, M. H. Yang, Y. C. Fan, W. C. Peng, and C. C. Hung, “Template-Based Headline Generator for Multiple Documents,” IEEE Access, vol. 10, pp. 46330–46341, 2022, doi: 10.1109/ACCESS.2022.3157287.

A. Li, T. Jiang, Q. Wang, and H. Yu, “The mixture of TextRank and LexRank techniques of single document automatic summarization research in Tibetan,” Proc. - 2016 8th Int. Conf. Intell. Human-Machine Syst. Cybern. IHMSC 2016, vol. 1, pp. 514–519, 2016, doi: 10.1109/IHMSC.2016.278.




DOI: https://doi.org/10.30645/kesatria.v4i3.216

DOI (PDF): https://doi.org/10.30645/kesatria.v4i3.216.g215

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: