Extractive Text Summarization Using Deep Learning for Tigrigna Language

Meresa Hiluf Gebrehiwot; Michael Melese

doi:doi:10.11648/j.ijdst.20230901.11

| Peer-Reviewed

Extractive Text Summarization Using Deep Learning for Tigrigna Language

Meresa Hiluf Gebrehiwot, Michael Melese

Published in International Journal on Data Science and Technology (Volume 9, Issue 1)

Received: 31 October 2022 Accepted: 4 January 2023 Published: 20 March 2023

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

With the ever-increasing amounts of textual material such as web pages, news articles, blogs, microblogs, and similar, the Internet became the massive body of unstructured information. In this paper to deal with the issues for the availability of more and more information with less time, the extractive text summarization using the deep learning model was used. In this paper, the proposed approach uses three basic stages of feature extraction, feature enhancement, and summary generation of the given news article to extract the core information, to produce well understandable summary and save reader’s time. In the feature extraction, We explore various features to improve the extracted sentences to the summary by the score and rank of the extracted features matrix by calculating the top thematic words, paragraph segmentation, sentences length & position, proper nouns, and TF-ISF, and the sum of the feature vector given to RBM to enhance the extracted feature vector and finally generate the final summarization by taking top high scores and 50% 0f the sum second higher scores from the enhanced feature extracted scores. For experimenting purpose, we have used 10 news articles from the total gathered news articles gathered from BBC-Tigrigna, Fana-Tigrigna and VOA-Tigrigna news website. The evaluation of the extracted summary was evaluated using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) to compare the system extracted summary with the reference / manual summary prepared by human experts. According the experimentation, the average score of ROUG-1 shows 49% for recall, 39% precession, 42% for F-score and for the ROUGE-2 shows that 32% recall, 26% precession and 28% for F-score, for ROUGE-l also shows that 39% of recall, 33% of Precession, and 35% of F-scores. The result shows the proposed approach have higher result in Rouge-1 and the F-score or harmonic mean of precision and recall is 42% and it solves the problems of information overloading in the ever-increasing available news articles by generating the extractive summarizations.

Published in	International Journal on Data Science and Technology (Volume 9, Issue 1)
DOI	10.11648/j.ijdst.20230901.11
Page(s)	1-12
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2023. Published by Science Publishing Group

Keywords

Extractive, Deep Learning, Restricted Boltzmann Machine (RBM), Sentence Features, Single Document, Summarization, Unsupervised

References

[1]	V. K. Dijana Kosmajac, "Automatic Text Summarization of News Articles in Serbian Language," 18th International Symposium INFOTEH-JAHORINA, pp. 20-22, 2019.
[2]	O. S. G. B. H. H. C. N. a. C. P. J. K. Yogan, "A review on automatic text summarization approaches," Journal of Computer Science, vol. 4, no. 12, p. 178–190, 2016.
[3]	A. Negash, "The Origin and Development of Tigrinya Language Publications (1886 - 1991) Volume One," University Library, vol. I, p. 131, 2016.
[4]	A. S. Akshay Kulkarni, "Natural Language Processing Recipes," in Unlocking Text Data with Machine Learning and Deep Learning using Python, Bangalore, Karnataka, India, acid-free paper, 2019, p. 253.
[5]	P. Anttila, "Automatic Text Summarization," UNIVERSITY OF TURKU, Department of Future Technologies, Computer Science, 2018.
[6]	J.-M. Torres-Moreno, Automatic Text Summarization, Great Britain, the United States: ISTE Ltd and John Wiley & Sons, Inc, 2014.
[7]	J. E. I. a. T. H. Gary Miner, "Practical text mining and statistical analysis for non-structured text data applications," Academic Press, 2012.
[8]	H. P. Luhn, "The automatic creation of literature abstracts.," IBM Journal of research and development, vol. 2 (2), p. 159–165, 1958.
[9]	H. P. Edmundson, "New methods in automatic extracting," Journal of the ACM J (JACM), vol. 2, no. 16, p. 264–285, 1969.
[10]	E. T. V. Leo Laugier, "Extractive Document Summarization Using Convolutional Neural Networks - Reimplementation," Department of Electrical Engineering and Computer Sciences.
[11]	Y. Kim, "Convolutional neural networks for sentence classification," arXiv preprint arXiv, vol. 1408., no. 5882, 2014.
[12]	M. J. E. P. Yong Zhang, "Extractive Document Summarization Based on Convolutional Neural Networks," IEEE, Singapore, Australia, 2016.
[13]	M. J. E. a. R. Z. Y. Zhang, "Multi-document extractive summarization using window-based sentence representation," in Computational Intelligence, 2015 IEEE Symposium Series on, p. 404–410, 2015.
[14]	J. O. A. M. C. M. M. P. L. H. C. &. J. C. F. B. De Sordi, "Design science research in practice: What can we learn from a longitudinal analysis of the development of published artifacts?," Informing Science: The International Journal of an Emerging Transdisciplin, no. 23, pp. 1-23, 2020.
[15]	J. v. &. H. A. &. M. A. Brocke, "Introduction to Design Science Research," In book: Design Science Research, 10.1007/978-3-030-46781-4_1., pp. 1-13, 2020.
[16]	M. T. &. K. K. Bharti Sharma, "Extractive text summarization using F-RBM," Journal of Statistics and Management Systems, pp. ISSN 2169-0014, 2020.
[17]	S. V. a. V. Nidhi, "Extractive Summarization using Deep Learning," Delhi Technological University: arXiv: 1708.04439v2 [cs. CL] 9 Jan 2019, no. arXiv: 1708.04439v2 [cs. CL] 9 Jan 2019, 2019.
[18]	a. M. S. Masoud Fatemi, "Joint Sentiment/Topic Modeling on Text Data Using Boosted Restricted Boltzmann Machine," in Department of Electrical and Computer Engineering, Isfahan University of Technology, Iran, 2017.
[19]	R. R. K. V. R. Ghosh, "A novel deep learning architecture for sentiment classification," 10.1109/RAIT.2016.7507953, 2016/03/01, pp. 511- 516.
[20]	G. A. Birhanu, "Automatic Text Summarizer for Tigrinya Language," Addis Ababa Unversity, Addis Ababa, 2017.

Cite This Article

Plain Text BibTeX RIS

APA Style

Meresa Hiluf Gebrehiwot, Michael Melese. (2023). Extractive Text Summarization Using Deep Learning for Tigrigna Language. International Journal on Data Science and Technology, 9(1), 1-12. https://doi.org/10.11648/j.ijdst.20230901.11

Copy | Download

ACS Style

Meresa Hiluf Gebrehiwot; Michael Melese. Extractive Text Summarization Using Deep Learning for Tigrigna Language. Int. J. Data Sci. Technol. 2023, 9(1), 1-12. doi: 10.11648/j.ijdst.20230901.11

Copy | Download

AMA Style

Meresa Hiluf Gebrehiwot, Michael Melese. Extractive Text Summarization Using Deep Learning for Tigrigna Language. Int J Data Sci Technol. 2023;9(1):1-12. doi: 10.11648/j.ijdst.20230901.11

Copy | Download

@article{10.11648/j.ijdst.20230901.11,
  author = {Meresa Hiluf Gebrehiwot and Michael Melese},
  title = {Extractive Text Summarization Using Deep Learning for Tigrigna Language},
  journal = {International Journal on Data Science and Technology},
  volume = {9},
  number = {1},
  pages = {1-12},
  doi = {10.11648/j.ijdst.20230901.11},
  url = {https://doi.org/10.11648/j.ijdst.20230901.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijdst.20230901.11},
  abstract = {With the ever-increasing amounts of textual material such as web pages, news articles, blogs, microblogs, and similar, the Internet became the massive body of unstructured information. In this paper to deal with the issues for the availability of more and more information with less time, the extractive text summarization using the deep learning model was used. In this paper, the proposed approach uses three basic stages of feature extraction, feature enhancement, and summary generation of the given news article to extract the core information, to produce well understandable summary and save reader’s time. In the feature extraction, We explore various features to improve the extracted sentences to the summary by the score and rank of the extracted features matrix by calculating the top thematic words, paragraph segmentation, sentences length & position, proper nouns, and TF-ISF, and the sum of the feature vector given to RBM to enhance the extracted feature vector and finally generate the final summarization by taking top high scores and 50% 0f the sum second higher scores from the enhanced feature extracted scores. For experimenting purpose, we have used 10 news articles from the total gathered news articles gathered from BBC-Tigrigna, Fana-Tigrigna and VOA-Tigrigna news website. The evaluation of the extracted summary was evaluated using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) to compare the system extracted summary with the reference / manual summary prepared by human experts. According the experimentation, the average score of ROUG-1 shows 49% for recall, 39% precession, 42% for F-score and for the ROUGE-2 shows that 32% recall, 26% precession and 28% for F-score, for ROUGE-l also shows that 39% of recall, 33% of Precession, and 35% of F-scores. The result shows the proposed approach have higher result in Rouge-1 and the F-score or harmonic mean of precision and recall is 42% and it solves the problems of information overloading in the ever-increasing available news articles by generating the extractive summarizations.},
 year = {2023}
}

Copy | Download

TY  - JOUR
T1  - Extractive Text Summarization Using Deep Learning for Tigrigna Language
AU  - Meresa Hiluf Gebrehiwot
AU  - Michael Melese
Y1  - 2023/03/20
PY  - 2023
N1  - https://doi.org/10.11648/j.ijdst.20230901.11
DO  - 10.11648/j.ijdst.20230901.11
T2  - International Journal on Data Science and Technology
JF  - International Journal on Data Science and Technology
JO  - International Journal on Data Science and Technology
SP  - 1
EP  - 12
PB  - Science Publishing Group
SN  - 2472-2235
UR  - https://doi.org/10.11648/j.ijdst.20230901.11
AB  - With the ever-increasing amounts of textual material such as web pages, news articles, blogs, microblogs, and similar, the Internet became the massive body of unstructured information. In this paper to deal with the issues for the availability of more and more information with less time, the extractive text summarization using the deep learning model was used. In this paper, the proposed approach uses three basic stages of feature extraction, feature enhancement, and summary generation of the given news article to extract the core information, to produce well understandable summary and save reader’s time. In the feature extraction, We explore various features to improve the extracted sentences to the summary by the score and rank of the extracted features matrix by calculating the top thematic words, paragraph segmentation, sentences length & position, proper nouns, and TF-ISF, and the sum of the feature vector given to RBM to enhance the extracted feature vector and finally generate the final summarization by taking top high scores and 50% 0f the sum second higher scores from the enhanced feature extracted scores. For experimenting purpose, we have used 10 news articles from the total gathered news articles gathered from BBC-Tigrigna, Fana-Tigrigna and VOA-Tigrigna news website. The evaluation of the extracted summary was evaluated using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) to compare the system extracted summary with the reference / manual summary prepared by human experts. According the experimentation, the average score of ROUG-1 shows 49% for recall, 39% precession, 42% for F-score and for the ROUGE-2 shows that 32% recall, 26% precession and 28% for F-score, for ROUGE-l also shows that 39% of recall, 33% of Precession, and 35% of F-scores. The result shows the proposed approach have higher result in Rouge-1 and the F-score or harmonic mean of precision and recall is 42% and it solves the problems of information overloading in the ever-increasing available news articles by generating the extractive summarizations.
VL  - 9
IS  - 1
ER  -

Copy | Download

Author Information

Meresa Hiluf Gebrehiwot

Faculty of Electrical/Electronics and ICT, Federal Technical and Vocational Education and Training Institute, Addis Ababa, Ethiopia
Michael Melese

School of Information Science, Addis Ababa University, Addis Ababa, Ethiopia

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Meresa Hiluf Gebrehiwot, Michael Melese. (2023). Extractive Text Summarization Using Deep Learning for Tigrigna Language. International Journal on Data Science and Technology, 9(1), 1-12. https://doi.org/10.11648/j.ijdst.20230901.11

Copy | Download

ACS Style

Meresa Hiluf Gebrehiwot; Michael Melese. Extractive Text Summarization Using Deep Learning for Tigrigna Language. Int. J. Data Sci. Technol. 2023, 9(1), 1-12. doi: 10.11648/j.ijdst.20230901.11

Copy | Download

AMA Style

Meresa Hiluf Gebrehiwot, Michael Melese. Extractive Text Summarization Using Deep Learning for Tigrigna Language. Int J Data Sci Technol. 2023;9(1):1-12. doi: 10.11648/j.ijdst.20230901.11

Copy | Download

@article{10.11648/j.ijdst.20230901.11,
  author = {Meresa Hiluf Gebrehiwot and Michael Melese},
  title = {Extractive Text Summarization Using Deep Learning for Tigrigna Language},
  journal = {International Journal on Data Science and Technology},
  volume = {9},
  number = {1},
  pages = {1-12},
  doi = {10.11648/j.ijdst.20230901.11},
  url = {https://doi.org/10.11648/j.ijdst.20230901.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijdst.20230901.11},
  abstract = {With the ever-increasing amounts of textual material such as web pages, news articles, blogs, microblogs, and similar, the Internet became the massive body of unstructured information. In this paper to deal with the issues for the availability of more and more information with less time, the extractive text summarization using the deep learning model was used. In this paper, the proposed approach uses three basic stages of feature extraction, feature enhancement, and summary generation of the given news article to extract the core information, to produce well understandable summary and save reader’s time. In the feature extraction, We explore various features to improve the extracted sentences to the summary by the score and rank of the extracted features matrix by calculating the top thematic words, paragraph segmentation, sentences length & position, proper nouns, and TF-ISF, and the sum of the feature vector given to RBM to enhance the extracted feature vector and finally generate the final summarization by taking top high scores and 50% 0f the sum second higher scores from the enhanced feature extracted scores. For experimenting purpose, we have used 10 news articles from the total gathered news articles gathered from BBC-Tigrigna, Fana-Tigrigna and VOA-Tigrigna news website. The evaluation of the extracted summary was evaluated using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) to compare the system extracted summary with the reference / manual summary prepared by human experts. According the experimentation, the average score of ROUG-1 shows 49% for recall, 39% precession, 42% for F-score and for the ROUGE-2 shows that 32% recall, 26% precession and 28% for F-score, for ROUGE-l also shows that 39% of recall, 33% of Precession, and 35% of F-scores. The result shows the proposed approach have higher result in Rouge-1 and the F-score or harmonic mean of precision and recall is 42% and it solves the problems of information overloading in the ever-increasing available news articles by generating the extractive summarizations.},
 year = {2023}
}

Copy | Download

TY  - JOUR
T1  - Extractive Text Summarization Using Deep Learning for Tigrigna Language
AU  - Meresa Hiluf Gebrehiwot
AU  - Michael Melese
Y1  - 2023/03/20
PY  - 2023
N1  - https://doi.org/10.11648/j.ijdst.20230901.11
DO  - 10.11648/j.ijdst.20230901.11
T2  - International Journal on Data Science and Technology
JF  - International Journal on Data Science and Technology
JO  - International Journal on Data Science and Technology
SP  - 1
EP  - 12
PB  - Science Publishing Group
SN  - 2472-2235
UR  - https://doi.org/10.11648/j.ijdst.20230901.11
AB  - With the ever-increasing amounts of textual material such as web pages, news articles, blogs, microblogs, and similar, the Internet became the massive body of unstructured information. In this paper to deal with the issues for the availability of more and more information with less time, the extractive text summarization using the deep learning model was used. In this paper, the proposed approach uses three basic stages of feature extraction, feature enhancement, and summary generation of the given news article to extract the core information, to produce well understandable summary and save reader’s time. In the feature extraction, We explore various features to improve the extracted sentences to the summary by the score and rank of the extracted features matrix by calculating the top thematic words, paragraph segmentation, sentences length & position, proper nouns, and TF-ISF, and the sum of the feature vector given to RBM to enhance the extracted feature vector and finally generate the final summarization by taking top high scores and 50% 0f the sum second higher scores from the enhanced feature extracted scores. For experimenting purpose, we have used 10 news articles from the total gathered news articles gathered from BBC-Tigrigna, Fana-Tigrigna and VOA-Tigrigna news website. The evaluation of the extracted summary was evaluated using Recall-Oriented Understudy for Gisting Evaluation (ROUGE) to compare the system extracted summary with the reference / manual summary prepared by human experts. According the experimentation, the average score of ROUG-1 shows 49% for recall, 39% precession, 42% for F-score and for the ROUGE-2 shows that 32% recall, 26% precession and 28% for F-score, for ROUGE-l also shows that 39% of recall, 33% of Precession, and 35% of F-scores. The result shows the proposed approach have higher result in Rouge-1 and the F-score or harmonic mean of precision and recall is 42% and it solves the problems of information overloading in the ever-increasing available news articles by generating the extractive summarizations.
VL  - 9
IS  - 1
ER  -

Copy | Download