---
title: "A New Approach for Arabic Text Summarization — Lagrini 2021"
description: "They argue that most earlier Arabic systems score sentences with bag-of-words statistics and ignore… 33 references, cited by 1 paper here."
authors: ["Samira Lagrini", "Mohammed Redjimi"]
year: 2021
venue: "Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021)"
source: "https://aclanthology.org/2021.icnlsp-1.20/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/lagrini-2021-new-approach-arabic-text-summarization/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lagrini-2021-new-approach-arabic-text-summarization/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/9/) / A New Approach for Arabic Text Summarization

# A New Approach for Arabic Text Summarization

**Authors:** Samira Lagrini and Mohammed Redjimi · **Year:** 2021 · **Venue:** [Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021)](https://md.research.elamur.ai/free/en/venues/icnlsp/) ([International Conference on Natural Language and Speech Processing 2021](https://md.research.elamur.ai/free/en/venues/icnlsp/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.icnlsp-1.20/) · [PDF](https://aclanthology.org/2021.icnlsp-1.20.pdf)

**Citations:** 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Lagrini and Redjimi address extractive summarization of Arabic text. They argue that most earlier Arabic systems score sentences with bag-of-words statistics and ignore discourse structure, which hurts coherence and readability. Their pipeline has two stages.

**Stage 1: rhetorical analysis (RST)**
- Sentences are split into EDUs using an Arabic discourse-marker lexicon built while annotating the authors' earlier Arabic RST corpus, plus segmentation rules.
- A multi-layer perceptron, fed lexical and semantic features, labels the explicit fine-grained relation between adjacent EDUs inside each sentence. Each label carries a nuclearity tag.
- Satellite EDUs, and EDUs in relations judged useless for summaries, are removed. The result is a primary summary.

**Stage 2: statistical ranking**
- The compressed sentences are ranked by similarity to the title, position and length.
- The top sentences are kept in their original order, up to the user's compression rate.

On 40 news articles from EASC at a 50% compression ratio, the system reaches ROUGE-1 recall 0.453 and precision 0.471, and ROUGE-2 recall 0.308 and precision 0.337. The work shows that discourse structure can be inserted ahead of cheap statistical scoring in a language with limited tooling.

## Key points
- The relation inventory has 23 fine-grained intra-sentential Arabic relations (from Lagrini et al., 2019a) in seven classes: causal, comparison, joint, elaboration, explanation, attribution and conditional. Each relation carries a nuclearity tag: NS, SN or NN.
- Relation identification is a multi-class MLP classifier over ten groups of lexical and semantic features computed for each adjacent EDU pair. Only explicit, marker-signalled relations are targeted.
- Compression follows three rules:
  - satellites are dropped;
  - EDUs in relations such as example-NS, simile-NS and contrast-NN are removed even when they are nuclei;
  - an EDU joined by an NN relation to a removed EDU is removed with it.
- The final sentence score is the sum of three terms:
  - title similarity;
  - position, which is 1 for the first or last sentence and 0.5 otherwise;
  - length, which is word count divided by the word count of the longest sentence in the primary summary.
- EASC contains 153 documents from Wikipedia, AlRai and Alwatan, covering ten topics, with five human references each (765 in total). Evaluation used a 40-article subset, ROUGE-1/ROUGE-2 and CR=50%. No baseline comparison is reported in the text.

## Interesting ideas
- Pruning by nuclearity keeps only the core clauses, and a deletion spreads to any NN partner of a removed unit, so equal-rank siblings are never split.
- The relation type can overrule nuclearity: some relations (example, simile, contrast) are discarded entirely because they rarely carry core content.
- The connective lexicon gathered while annotating a corpus is reused directly as the segmenter, and each marker also signals which explicit relation applies (e.g. "because" points to a causal relation).
- Statistics are computed after linguistic filtering, so their meaning changes. Once satellites are gone, a longer sentence plausibly holds more core content, so length becomes a useful signal.
- Each system output is scored against five independent human references rather than one, which softens the bias of a single annotator.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (back): the text → graph → text compressor could mark clause nodes as nucleus or satellite and drop satellites together with their coordinate siblings, giving an explainable reason for every removed clause.
- **I2** (back): when generating condensed retellings, a small explicit list of relation types to skip would keep illustrative and comparative asides out of the output, and each skip could be traced to its rule.
- **I3** (frames): prag could use an English connective lexicon to split clauses and attach explicit discourse relations between frames, keeping implicit relations as a separate, harder case.
- **I4** (answer): in QA over fables, ranking candidate evidence sentences only after reducing them to their nuclear clauses could make simple heuristics like length or title overlap more reliable.
- **I5** (learn): evaluation of generated retellings or summaries could compare against several reference versions, so that valid alternative phrasings are not counted as errors.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works

🧭 Topics (3): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works · [🧵 Discourse analysis](https://md.research.elamur.ai/free/en/topics/discourse-analysis/) · 471 works · [📝 Summarization](https://md.research.elamur.ai/free/en/topics/summarization/) · 243 works

## Cite

Cite as: Samira Lagrini and Mohammed Redjimi. 2021. A New Approach for Arabic Text Summarization. Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{lagrini2021new,
  title = {{A New Approach for Arabic Text Summarization}},
  author = {Samira Lagrini and Mohammed Redjimi},
  booktitle = {Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021)},
  year = {2021},
  url = {https://aclanthology.org/2021.icnlsp-1.20/}
}
```

- [← previous A Corpus-Based Approach to the Lemmatisation of Old English Superlative Adverbs](https://md.research.elamur.ai/free/en/papers/bghiyel-2021-corpus-based-approach-lemmatisation-old/)
- [next → Analysis of Data Augmentation Methods for Low-Resource Maltese ASR](https://md.research.elamur.ai/free/en/papers/demarco-2021-analysis-data-augmentation-methods-low/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/9/)

## References

33 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Luhn, H. P. 1958. The automatic creation of literature abstracts. IBM Journal of research and development, 2(2): 159-165. [find](https://scholar.google.com/scholar?q=Luhn%2C+H%2E+P%2E+1958%2E+The+automatic+creation+of+literature+abstracts%2E+IBM+Journal+of+research+and+development%2C+2%282%29%3A+159%2D165%2E)
2. Baxendale, P. B. 1958. Machine-made index for technical literature—an experiment. IBM Journal of Research and Development, 2(4): 354-361. [find](https://scholar.google.com/scholar?q=Baxendale%2C+P%2E+B%2E+1958%2E+Machine%2Dmade+index+for+technical+literature%E2%80%94an+experiment%2E+IBM+Journal+of+Research+and+Development%2C+2%284%29%3A+354%2D361%2E)
3. Edmundson, H. P. 1969. New methods in automatic extracting. Journal of the ACM (JACM), 16(2): 264-285 Fouad Soufiane, Douzidia, and Guy Lapalme. (2004). Lakhas, an Arabic summarization system. In Proceedings of DUC (Vol. 4), pages 128-135. [find](https://scholar.google.com/scholar?q=Edmundson%2C+H%2E+P%2E+1969%2E+New+methods+in+automatic+extracting%2E+Journal+of+the+ACM+%28JACM%29%2C+16%282%29%3A+264%2D285+Fouad+Soufiane%2C+Douzidia%2C+and+Guy+Lapalme%2E+%282004%29%2E+Lakhas%2C+an+Arabic+summarization+system%2E+In+Proc)
4. Alotaiby, F., Foda, S., Alkharashi, I. 2012. New approaches to automatic headline generation for Arabic documents. Journal of Engineering and Computer Innovations, 3(1):11-25. [find](https://scholar.google.com/scholar?q=Alotaiby%2C+F%2E%2C+Foda%2C+S%2E%2C+Alkharashi%2C+I%2E+2012%2E+New+approaches+to+automatic+headline+generation+for+Arabic+documents%2E+Journal+of+Engineering+and+Computer+Innovations%2C+3%281%29%3A11%2D25%2E)
5. Ibrahim, Sobh, Nevin Darwish, and Magda Fayek.. 2006. An optimized dual classification system for Arabic extractive generic text summarization. In Proceedings of the 7th Conference on Language Engineering, pages 149–154. [find](https://scholar.google.com/scholar?q=Ibrahim%2C+Sobh%2C+Nevin+Darwish%2C+and+Magda+Fayek%2E%2E+2006%2E+An+optimized+dual+classification+system+for+Arabic+extractive+generic+text+summarization%2E+In+Proceedings+of+the+7th+Conference+on+Language+Enginee)
6. Fattah, M. A., Ren, F. 2009. GA, MR, FFNN, PNN and GMM based models for automatic text summarization. Computer Speech & Language, 23(1):126-144. [find](https://scholar.google.com/scholar?q=Fattah%2C+M%2E+A%2E%2C+Ren%2C+F%2E+2009%2E+GA%2C+MR%2C+FFNN%2C+PNN+and+GMM+based+models+for+automatic+text+summarization%2E+Computer+Speech+%26+Language%2C+23%281%29%3A126%2D144%2E)
7. Mohamed Mahdi, Boudabous, Mohamed Hédi Maaloul, and Lamia Hadrich Belguith. 2010. Digital learning for summarizing Arabic documents. In proceeding of International Conference on Natural Language Processing, pages 79-84. Springer, Berlin, Heidelberg. [find](https://scholar.google.com/scholar?q=Mohamed+Mahdi%2C+Boudabous%2C+Mohamed+H%C3%A9di+Maaloul%2C+and+Lamia+Hadrich+Belguith%2E+2010%2E+Digital+learning+for+summarizing+Arabic+documents%2E+In+proceeding+of+International+Conference+on+Natural+Language+Proce)
8. Riadh Belkebir, Ahmed Guessoum. 2015. A supervised approach to Arabic text summarization using adaboost. In New contributions in information systems and technologies, pages 227-236. [find](https://scholar.google.com/scholar?q=Riadh+Belkebir%2C+Ahmed+Guessoum%2E+2015%2E+A+supervised+approach+to+Arabic+text+summarization+using+adaboost%2E+In+New+contributions+in+information+systems+and+technologies%2C+pages+227%2D236%2E)
9. Springer International Publishing Al-Radaideh, Q. A., Bataineh, D. Q. 2018. A Hybrid Approach for Arabic Text Summarization Using Domain Knowledge and Genetic Algorithms. Cognitive Computation, pages 1-19. [find](https://scholar.google.com/scholar?q=Springer+International+Publishing+Al%2DRadaideh%2C+Q%2E+A%2E%2C+Bataineh%2C+D%2E+Q%2E+2018%2E+A+Hybrid+Approach+for+Arabic+Text+Summarization+Using+Domain+Knowledge+and+Genetic+Algorithms%2E+Cognitive+Computation%2C+pages+)
10. Qaroush, A., Farha, I. A., Ghanem, W., Washaha, M., & Maali, E. 2019. An efficient single document Arabic text summarization using a combination of statistical and semantic features. Journal of King Saud University- Computer and Information Sciences, https://doi.org/10.1016/j.jksuci.2019.03.010. [↗](https://doi.org/10.1016/j.jksuci.2019.03.010)
11. Mahmoud El-Haj, Udo Kruschwitz, and Chris Fox. 2011. Exploring clustering for multi-document Arabic summarisation. In Asia Information Retrieval Symposium, pages 550-561. Springer, Berlin, Heidelberg. [find](https://scholar.google.com/scholar?q=Mahmoud+El%2DHaj%2C+Udo+Kruschwitz%2C+and+Chris+Fox%2E+2011%2E+Exploring+clustering+for+multi%2Ddocument+Arabic+summarisation%2E+In+Asia+Information+Retrieval+Symposium%2C+pages+550%2D561%2E+Springer%2C+Berlin%2C+Heidelberg%2E)
12. Oufaida, H., Nouali, O., Blache, P. 2014. Minimum redundancy and maximum relevance for single and multi-document Arabic text summarization. Journal of King Saud University-Computer and Information Sciences, 26(4): 450-461. [find](https://scholar.google.com/scholar?q=Oufaida%2C+H%2E%2C+Nouali%2C+O%2E%2C+Blache%2C+P%2E+2014%2E+Minimum+redundancy+and+maximum+relevance+for+single+and+multi%2Ddocument+Arabic+text+summarization%2E+Journal+of+King+Saud+University%2DComputer+and+Information+Sci)
13. Hamzah Noori, Fejer, Nazlia, Omar. 2014. Automatic Arabic text summarization using clustering and keyphrase extraction. In proceeding of International Conference on Information Technology and Multimedia (ICIMU), IEEE. Putrajaya, Malaysia, pages 293-298. [find](https://scholar.google.com/scholar?q=Hamzah+Noori%2C+Fejer%2C+Nazlia%2C+Omar%2E+2014%2E+Automatic+Arabic+text+summarization+using+clustering+and+keyphrase+extraction%2E+In+proceeding+of+International+Conference+on+Information+Technology+and+Multimed)
14. Waheeb, S. A., Khan, N. A., Chen, B., and Shang, X. 2020. Multi-document Arabic text summarization based on clustering and Word2Vec to reduce redundancy. Information, 11(2), 59. [find](https://scholar.google.com/scholar?q=Waheeb%2C+S%2E+A%2E%2C+Khan%2C+N%2E+A%2E%2C+Chen%2C+B%2E%2C+and+Shang%2C+X%2E+2020%2E+Multi%2Ddocument+Arabic+text+summarization+based+on+clustering+and+Word2Vec+to+reduce+redundancy%2E+Information%2C+11%282%29%2C+59%2E)
15. Alqaisi, R., Ghanem, W., and Qaroush, A. 2020. Extractive Multi-Document Arabic Text Summarization Using Evolutionary Multi-Objective Optimization With K-Medoid Clustering. IEEE Access, 8 : 228206-228224. [find](https://scholar.google.com/scholar?q=Alqaisi%2C+R%2E%2C+Ghanem%2C+W%2E%2C+and+Qaroush%2C+A%2E+2020%2E+Extractive+Multi%2DDocument+Arabic+Text+Summarization+Using+Evolutionary+Multi%2DObjective+Optimization+With+K%2DMedoid+Clustering%2E+IEEE+Access%2C+8+%3A+228206%2D228)
16. Alami, N., Meknassi, M., En-nahnahi, N., El Adlouni, Y., & Ammor, O. 2021. Unsupervised neural networks for automatic Arabic text summarization using document clustering and topic modeling. Expert Systems with Applications, 172: 114652. [find](https://scholar.google.com/scholar?q=Alami%2C+N%2E%2C+Meknassi%2C+M%2E%2C+En%2Dnahnahi%2C+N%2E%2C+El+Adlouni%2C+Y%2E%2C+%26+Ammor%2C+O%2E+2021%2E+Unsupervised+neural+networks+for+automatic+Arabic+text+summarization+using+document+clustering+and+topic+modeling%2E+Expert+Sys)
17. Nabil, ALAMI, Yassine El Adlouni, Noureddine En-nahnahi, Mohammed Meknassi. 2017. Using Statistical and Semantic Analysis for Arabic Text Summarization. In proceeding of International Conference on Information Technology and Communication Systems, Springer, Cham, pages 35-50. [find](https://scholar.google.com/scholar?q=Nabil%2C+ALAMI%2C+Yassine+El+Adlouni%2C+Noureddine+En%2Dnahnahi%2C+Mohammed+Meknassi%2E+2017%2E+Using+Statistical+and+Semantic+Analysis+for+Arabic+Text+Summarization%2E+In+proceeding+of+International+Conference+on+In)
18. Kumar, Y. J., Goh, O. S., Halizah, B., Ngo, H. C., Puspalata, C. 2016. A review on automatic text summarization approaches. Journal of Computer Science, 12(4):178-190. [find](https://scholar.google.com/scholar?q=Kumar%2C+Y%2E+J%2E%2C+Goh%2C+O%2E+S%2E%2C+Halizah%2C+B%2E%2C+Ngo%2C+H%2E+C%2E%2C+Puspalata%2C+C%2E+2016%2E+A+review+on+automatic+text+summarization+approaches%2E+Journal+of+Computer+Science%2C+12%284%29%3A178%2D190%2E)
19. Azmi, A. M., Al-Thanyyan, S. 2012. A text summarizer for Arabic. Computer Speech & Language, 26(4), pp. 260-273. [find](https://scholar.google.com/scholar?q=Azmi%2C+A%2E+M%2E%2C+Al%2DThanyyan%2C+S%2E+2012%2E+A+text+summarizer+for+Arabic%2E+Computer+Speech+%26+Language%2C+26%284%29%2C+pp%2E+260%2D273%2E)
20. Al Khawaldeh, F., Samawi, V. 2015. Lexical cohesion and entailment based segmentation for Arabic text summarization (LCEAS). The World of Computer Science and Information Technology Journal (WSCIT), 5(3):51-60. [find](https://scholar.google.com/scholar?q=Al+Khawaldeh%2C+F%2E%2C+Samawi%2C+V%2E+2015%2E+Lexical+cohesion+and+entailment+based+segmentation+for+Arabic+text+summarization+%28LCEAS%29%2E+The+World+of+Computer+Science+and+Information+Technology+Journal+%28WSCIT%29%2C+5)
21. Azmi, A. M., and Altmami, N. I. 2018. An abstractive Arabic text summarizer with user controlled granularity. Information Processing & Management, 54(6): 903-921. [find](https://scholar.google.com/scholar?q=Azmi%2C+A%2E+M%2E%2C+and+Altmami%2C+N%2E+I%2E+2018%2E+An+abstractive+Arabic+text+summarizer+with+user+controlled+granularity%2E+Information+Processing+%26+Management%2C+54%286%29%3A+903%2D921%2E)
22. Mann, W. C., Thompson, S. A. 1988. [Rhetorical structure theory: Toward a functional theory of text organization](https://md.research.elamur.ai/free/en/papers/mann-1988-rhetorical-structure-theory-functional/). Text-Interdisciplinary Journal for the Study of Discourse, 8(3):243-281.
23. Taboada, M., and Mann, W. C. 2006. Rhetorical structure theory: Looking back and moving ahead. Discourse studies, 8(3): 423-459. [find](https://scholar.google.com/scholar?q=Taboada%2C+M%2E%2C+and+Mann%2C+W%2E+C%2E+2006%2E+Rhetorical+structure+theory%3A+Looking+back+and+moving+ahead%2E+Discourse+studies%2C+8%283%29%3A+423%2D459%2E)
24. Lynn Carlson, Daniel Marcu, Mary Ellen Okurowski. 2003. [Building a discourse-tagged corpus in the framework of rhetorical structure theory](https://md.research.elamur.ai/free/en/papers/carlson-2001-building-discourse-tagged-corpus-framework/). In: van Kuppevelt J., Smith R.W. (eds) Current and New Directions in Discourse and Dialogue. Text, Speech and Language Technology, volume 22, page 85-112, Springer, Dordrecht. https://doi.org/10.1007/978-94-010-0019-2_5 [↗](https://doi.org/10.1007/978-94-010-0019-2_5)
25. Lagrini, S., Azizi, N., Redjimi, M., and Dwairi, M. A. 2019. Automatic identification of rhetorical relations among intra-sentence discourse segments in Arabic. International Journal of Intelligent Systems Technologies and Applications, 18(3): 281-302. [find](https://scholar.google.com/scholar?q=Lagrini%2C+S%2E%2C+Azizi%2C+N%2E%2C+Redjimi%2C+M%2E%2C+and+Dwairi%2C+M%2E+A%2E+2019%2E+Automatic+identification+of+rhetorical+relations+among+intra%2Dsentence+discourse+segments+in+Arabic%2E+International+Journal+of+Intelligent+Sy)
26. Lagrini, S., Azizi, N., Redjimi, M., and Dwairi, M. A. 2019a. Toward an automatic summarisation of Arabic text depending on rhetorical relations. International Journal of Reasoning-based Intelligent Systems, 11(3): 203-214. Attia, Mohammed. [find](https://scholar.google.com/scholar?q=Lagrini%2C+S%2E%2C+Azizi%2C+N%2E%2C+Redjimi%2C+M%2E%2C+and+Dwairi%2C+M%2E+A%2E+2019a%2E+Toward+an+automatic+summarisation+of+Arabic+text+depending+on+rhetorical+relations%2E+International+Journal+of+Reasoning%2Dbased+Intelligent+S)
27. A. 2007. Arabic tokenization system. In Proceedings of the 2007 workshop on computational approaches to semitic languages: Common issues and resources, pages 65-72. [find](https://scholar.google.com/scholar?q=A%2E+2007%2E+Arabic+tokenization+system%2E+In+Proceedings+of+the+2007+workshop+on+computational+approaches+to+semitic+languages%3A+Common+issues+and+resources%2C+pages+65%2D72%2E)
28. Maha Althobaiti, Udo Kruschwitz, Massimo Poesio. 2014. [AraNLP: A Java-based library for the processing of Arabic text](https://md.research.elamur.ai/free/en/papers/althobaiti-2014-aranlp-java-based-library-processing/). In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC), pages 4134-4138.
29. El-Khair, I. A. (2006). Effects of stop words elimination for Arabic information retrieval: a comparative study. International Journal of Computing & Information Sciences, 4(3): 119-133. [find](https://scholar.google.com/scholar?q=El%2DKhair%2C+I%2E+A%2E+%282006%29%2E+Effects+of+stop+words+elimination+for+Arabic+information+retrieval%3A+a+comparative+study%2E+International+Journal+of+Computing+%26+Information+Sciences%2C+4%283%29%3A+119%2D133%2E)
30. Nabil Alami; Mohammed Meknassi; Said Alaoui Ouatik; NourEddine Ennahnahi. 2016. Impact of stemming on Arabic text summarization. In 2016 4th IEEE International Colloquium on Information Science and Technology (CiSt), IEEE, pages 338-343. [find](https://scholar.google.com/scholar?q=Nabil+Alami%3B+Mohammed+Meknassi%3B+Said+Alaoui+Ouatik%3B+NourEddine+Ennahnahi%2E+2016%2E+Impact+of+stemming+on+Arabic+text+summarization%2E+In+2016+4th+IEEE+International+Colloquium+on+Information+Science+and+Te)
31. Shereen Khoja and Roger Garside. (1999). Stemming Arabic text. Lancaster, UK, Computing Department, Lancaster University. [find](https://scholar.google.com/scholar?q=Shereen+Khoja+and+Roger+Garside%2E+%281999%29%2E+Stemming+Arabic+text%2E+Lancaster%2C+UK%2C+Computing+Department%2C+Lancaster+University%2E)
32. Al-Abdallah, R. Z., Al-Taani, A. T. 2017. Arabic Single-Document Text Summarization Using Particle Swarm Optimization Algorithm. Procedia Computer Science, 117: 30-37. El Haj, M., Kruschwitz, U., Fox, C. (2010).Using Mechanical Turk to Create a Corpus of Arabic Summaries. Editors & Workshop Chairs, pages 36-39. [find](https://scholar.google.com/scholar?q=Al%2DAbdallah%2C+R%2E+Z%2E%2C+Al%2DTaani%2C+A%2E+T%2E+2017%2E+Arabic+Single%2DDocument+Text+Summarization+Using+Particle+Swarm+Optimization+Algorithm%2E+Procedia+Computer+Science%2C+117%3A+30%2D37%2E+El+Haj%2C+M%2E%2C+Kruschwitz%2C+U%2E%2C+Fox%2C)
33. Chin-Yew, Lin. 2004. [ROUGE: A Package for Automatic Evaluation of Summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). Proceedings of Workshop on Text Summarization Branches Out, Barcelona, Spain, pages: 74-81.

*Updated 2 November 2026*