Bilingual automatic text summarization using unsupervised deep learning

Singh, Shashi Pal; Kumar, Ajai; Mangal, Abhilasha; Singhal, Shikha

doi:10.1109/iceeot.2016.7754874

Cited by 31 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is evaluated by number of occurrences for term. The largest TF for in evolution used are TF-ISF [12,13] and TF-IDF [14].…”

Section: Term Frequency (Tf)mentioning

confidence: 99%

Extractive Text Summarization Using Recent Approaches: A Survey

Yadav¹,

Maurya²,

Ranvijay³

et al. 2021

ISI

View full text Add to dashboard Cite

In this era of growing digital media, the volume of text data increases day by day from various sources and may contain entire documents, books, articles, etc. This amount of text is a source of information that may be insignificant, redundant, and sometimes may not carry any meaningful representation. Therefore, we require some techniques and tools that can automatically summarize the enormous amounts of text data and help us to decide whether they are useful or not. Text summarization is a process that generates a brief version of the document in the form of a meaningful summary. It can be classified into abstractive text summarization and extractive text summarization. Abstractive text summarization generates an abstract type of summary from the given document. In extractive text summarization, a summary is created from the given document that contains crucial sentences of the document. Many authors proposed various techniques for both types of text summarization. This paper presents a survey of extractive text summarization on graphical-based techniques. Specifically, it focuses on unsupervised and supervised techniques. This paper shows the recent works and advances on them and focuses on the strength and weaknesses of surveys of previous works in tabular form. At last, it concentrates on the evaluation measure techniques of summary.

show abstract

“…This is evaluated by number of occurrences for term. The largest TF for in evolution used are TF-ISF [12,13] and TF-IDF [14].…”

Section: Term Frequency (Tf)mentioning

confidence: 99%

Extractive Text Summarization Using Recent Approaches: A Survey

Yadav¹,

Maurya²,

Ranvijay³

et al. 2021

ISI

View full text Add to dashboard Cite

show abstract

“…Digunakan metode RBM karena dapat memberikan hasil yang lebih baik dalam peringkasan. Dalam penelitian ini, metode RBM digunakan untuk meningkatkan nilai fitur setiap kalimat sehingga ringkasan yang dihasilkan lebih akurat [7]. Gambar…”

Section: Peringkasan Teks Ekstraktif Pada Dokumen Tunggal Menggunakan Metode Restricted Boltzmann Machineunclassified

“…Apabila jumlah kata dalam kalimat kurang dari 3 maka nilai fiturnya bernilai 0. Sedangkan untuk yang lainnya dalam menentukan kalimat penting berdasarkan panjang kalimatnya dapat dihitung menggunakan persamaan (2) [7], [8].…”

Section: Fitur Panjang Kalimatunclassified

See 1 more Smart Citation

Peringkasan Teks Ekstraktif pada Dokumen Tunggal Menggunakan Metode Restricted Boltzmann Machine

Widiastutik

Santoso

2019

INSYST

View full text Add to dashboard Cite

Penelitian yang dilakukan yaitu menghasilkan peringkasan teks ekstratif secara otomatis yang dapat membantu menghasilkan dokumen yang lebih pendek dari dokumen aslinya dengan cara mengambil kalimat penting dari dokumen sehingga pembaca dapat memahami isi dokumen dengan cepat tanpa membaca secara keseluruhan. Dataset yang digunakan sebanyak 30 dokumen tunggal teks berita berbahasa Indonesia yang diperoleh dari www.kompas.com pada kategori tekno. Dalam penelitian ini, digunakan sepuluh fitur yaitu posisi kalimat, panjang kalimat, data numerik, bobot kalimat, kesamaan antara kalimat dan centroid, bi-gram, tri-gram, kata benda yang tepat, kemiripan antar kalimat, huruf besar. Nilai fitur setiap kalimat dihitung. Nilai fitur yang dihasilkan ditingkatkan dengan menggunakan metode Restricted Boltzmann Machine (RBM) agar ringkasan yang dihasilkan lebih akurat. Untuk proses pengujian dalam penelitian ini menggunakan ROUGE-1. Hasil yang diperoleh dalam penelitian yaitu dengan menggunakan learning rate 0.06 menghasilkan recall, precision dan f-measure tertinggi yakni 0.744, 0.611 dan 0.669. Selain itu, semakin besar nilai compression rate yang digunakan maka hasil recall, precision dan f-measure yang dihasilkan akan semakin tinggi. Hasil peringkasan teks dengan menggunakan RBM memiliki nilai recall lebih tinggi 2.1%, precision lebih tinggi 1.6% dan f-measure lebih tinggi 1.8% daripada hasil peringkasan teks tanpa RBM. Hal ini menunjukkan bahwa peringkasan teks dengan menggunakan RBM hasilnya lebih baik daripada peringkasan teks tanpa RBM.

show abstract

“…There have been many studies to apply artificial intelligence techniques to automatic text summarization: deep learning [Singh, S. P. et al, 2016], reinforcement learning [Lee, G. H. and Lee, K. J., 2017], and genetic algorithms [Meena, Y. K. and Gopalani, D., 2015] for example. However, such AI techniques are computationally intensive, and techniques based on text features are still important and effective, because such conventional techniques are comparatively lightweight.…”

Section: Introductionmentioning

confidence: 99%

Automatic Text Summarization Using Semantically Extended Word Position Information

Samejima¹,

Matsumoto²,

Yoshida³

2019

17th International Conference on E-Society 2019

View full text Add to dashboard Cite

Many automatic text summarization services use extractive methods, which pick up sentences according to their importance out of a given document. The importance is estimated using several metrics such as position information and semantic information. Most methods combine these metrics using weighted linear summation. This paper proposes more fine-grained integration of position information and semantic information to achieve better estimation of importance, which leads to better quality of summaries.

show abstract

Bilingual automatic text summarization using unsupervised deep learning

Cited by 31 publications

References 7 publications

Extractive Text Summarization Using Recent Approaches: A Survey

Extractive Text Summarization Using Recent Approaches: A Survey

Peringkasan Teks Ekstraktif pada Dokumen Tunggal Menggunakan Metode Restricted Boltzmann Machine

Automatic Text Summarization Using Semantically Extended Word Position Information

Contact Info

Product

Resources

About