---
title: "Keyphrase Based Arabic Summarizer (KPAS) (2012)"
description: "The keyphrase stage builds on the earlier Arabic extractor AKE. 94.8% accuracy. 24 references, cited by 1 paper here."
authors: ["Tarek El-Shishtawy", "Fatma El-Ghannam"]
year: 2012
venue: "arXiv:1206.5384"
source: "https://arxiv.org/abs/1206.5384"
doi: "10.48550/arxiv.1206.5384"
arxiv: "1206.5384"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/el-shishtawy-2012-keyphrase-based-arabic-summarizer-kpas/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/el-shishtawy-2012-keyphrase-based-arabic-summarizer-kpas/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2012](https://md.research.elamur.ai/free/en/papers/2012/page/3/) / Keyphrase Based Arabic Summarizer (KPAS)

# Keyphrase Based Arabic Summarizer (KPAS)

**Authors:** [Tarek El-Shishtawy](https://md.research.elamur.ai/free/en/authors/tarek-el-shishtawy/) and [Fatma El-Ghannam](https://md.research.elamur.ai/free/en/authors/fatma-el-ghannam/) · **Year:** 2012 · **Venue:** arXiv:1206.5384 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1206.5384) · [PDF](https://arxiv.org/pdf/1206.5384) · [DOI 10.48550/arxiv.1206.5384](https://doi.org/10.48550/arxiv.1206.5384) · [arXiv 1206.5384](https://arxiv.org/abs/1206.5384) · [OpenAlex](https://openalex.org/W2148441602)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/el-shishtawy-2012-keyphrase-based-arabic-summarizer-kpas/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses generic extractive summarization of Arabic documents, a setting with no standard reference summaries. KPAS first finds the document's keyphrases and then uses them, instead of scoring sentences directly, to rank sentences for selection. The keyphrase stage builds on the earlier Arabic extractor AKE. The authors replaced its corpus-based linguistic module with a root-based lemmatizer, so words are represented at the lemma level. That level sits between over-merging roots and under-merging stems. Four sentence-scoring heuristics are proposed, each aimed at a different goal: informativeness, preventing one main topic from dominating, low redundancy, and full topic coverage. A fourth heuristic adds up the normalized scores to balance these goals. For evaluation, the authors summarize Arabic texts that have aligned English versions at 25% compression. They map the chosen sentences to English and compare them with the output of the established English Extractor system, finding about 66% average overlap. The work matters as an early, cheap, largely language-independent Arabic summarizer, and the authors present it as the first to use automatically extracted keyphrases for Arabic summaries.

## Key points
- KPAS has two subsystems, a keyphrase extractor (a modified AKE) and a sentence extractor. Sentences are taken in decreasing rank order until the target length or percentage is reached.
- The plugged-in lemmatizer reaches up to 94.8% accuracy, and 89.15% on documents it has not seen before.
- There are four heuristics. The coverage one (NKS) picks at most one sentence per keyphrase, namely the first sentence where that keyphrase appears. The merging score is NSS + NCS + NKS.
- Evaluation uses 25% compression on aligned English/Arabic texts, such as a UNICEF report excerpt. Similarity to the English Extractor summaries averages roughly 66%.
- The authors acknowledge that other compression ratios have not yet been evaluated.

## Interesting ideas
- Coverage-first selection: process keyphrases from highest to lowest score and add only the earliest sentence containing each one, which limits redundancy and ensures every major topic appears.
- Balancing goals by summing normalized scores: each heuristic's score is scaled by its maximum and then added, so no single criterion dominates and each criterion's contribution stays transparent.
- Sentence importance depends on the length budget: whether a sentence is worth including depends on the allowed compression, not only on a fixed per-sentence score.
- Evaluating across languages with parallel text: when a language lacks gold summaries, summarize it, project the selected sentences onto an aligned English text, and compare with a trusted English system.
- Lemma as the middle granularity: grouping word forms by lemma avoids both the over-merging of roots and the under-merging of stems, for example by uniting broken plurals with their singulars.

## 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 pick one realizing sentence per salient entity or frame, so that compressed output covers all key participants without repeating them.
- **I2** (back): Generation could rank candidate sentences with an explicit sum of per-goal normalized scores (salience, coverage, novelty), and the explanation could report each component.
- **I3** (answer): Readers producing short versus long answers could re-rank supporting facts depending on how many they are allowed to output, rather than applying one fixed threshold.
- **I4** (learn): Mova's translation path through the meta-world could be checked the same way, by comparing projected selections or graphs against an independent English witness instead of a gold standard.
- **I5** (tokens): Keyphrase and salience features in the en crate should be counted over lemmas, so that irregular forms like "children" and "child" add to the same concept.

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

## Institutions

- [Benha University](https://md.research.elamur.ai/free/en/universities/benha-university/) — University, Banhā, Egypt · 14 works · 89 citations
- [Electronics Research Institute](https://md.research.elamur.ai/free/en/labs/electronics-research-institute/) — Research institute, Giza, Egypt · 2 works · 36 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [📝 Summarization](https://md.research.elamur.ai/free/en/topics/summarization/) · 232 works

## Cite

Cite as: Tarek El-Shishtawy and Fatma El-Ghannam. 2012. Keyphrase Based Arabic Summarizer (KPAS). arXiv:1206.5384.

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

```bibtex
@misc{elshishtawy2012keyphrase,
  title = {{Keyphrase Based Arabic Summarizer (KPAS)}},
  author = {Tarek El-Shishtawy and Fatma El-Ghannam},
  year = {2012},
  doi = {10.48550/arxiv.1206.5384},
  eprint = {1206.5384},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1206.5384}
}
```

- [← previous Handling Unknown Words in Arabic FST Morphology](https://md.research.elamur.ai/free/en/papers/shaalan-2012-handling-unknown-words-arabic-fst/)
- [next → Parsing Any Domain English text to CoNLL dependencies](https://md.research.elamur.ai/free/en/papers/kolachina-2012-parsing-any-domain-english-text/)
- [↑ back to papers of 2012](https://md.research.elamur.ai/free/en/papers/2012/page/3/)

## References

24 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Barzilay R, Elhadad M, [Using Lexical Chains for Text Summarization](https://md.research.elamur.ai/free/en/papers/barzilay-1997-lexical-chains-text-summarization/), Proceedings of the ACL Workshop on Intelligent Scalable Text Summarization, 1997.
2. D'Avanzo, E., Magnini, B., Vallin, A Keyphrase Extraction for Summarization Purposes: The LAKE System at DUC-2004. In the Document Understanding Workshop (presented at the HLT/NAACL Annual Meeting, Boston, USA, 2004. [find](https://scholar.google.com/scholar?q=D%27Avanzo%2C+E%2E%2C+Magnini%2C+B%2E%2C+Vallin%2C+A+Keyphrase+Extraction+for+Summarization+Purposes%3A+The+LAKE+System+at+DUC%2D2004%2E+In+the+Document+Understanding+Workshop+%28presented+at+the+HLT%2FNAACL+Annual+Meeting%2C+Bo)
3. Edmunson, H. Newm methods in automatic extracting. Journal of the ACM 16(2), 1969. [find](https://scholar.google.com/scholar?q=Edmunson%2C+H%2E+Newm+methods+in+automatic+extracting%2E+Journal+of+the+ACM+16%282%29%2C+1969%2E)
4. El-Beltagy, S.R. & Rafea A. KP-Miner: A Keyphrase Extraction System for English and Arabic Documents. Information systems, doi: 10.1016/j.is. 2008.05.002, 2008 [↗](https://doi.org/10.1016/j.is)
5. El-Shishtawy T and El-Ghannam F, " [An Accurate Arabic Root-Based Lemmatizer for Information Retrieval Purposes](https://md.research.elamur.ai/free/en/papers/el-shishtawy-2012-accurate-arabic-root-based-lemmatizer/)," International Journal of Computer Science Issues, Volume 9, Issue 1, January 2012. [↗](https://doi.org/10.48550/arxiv.1203.3584)
6. El-Shishtawy T and. Al-sammak A, "Arabic Keyphrase Extraction using Linguistic knowledge and Machine Learning Techniques", Proceedings of the Second International Conference on Arabic Language Resources and Tools, The MEDAR Consortium, Cairo, Egypt. 2009. [find](https://scholar.google.com/scholar?q=El%2DShishtawy+T+and%2E+Al%2Dsammak+A%2C+%22Arabic+Keyphrase+Extraction+using+Linguistic+knowledge+and+Machine+Learning+Techniques%22%2C+Proceedings+of+the+Second+International+Conference+on+Arabic+Language+Resourc)
7. Frank E, Paynter G.W., Witten I.H., Gutwin C. and Nevill-Manning C.G. (1999) "Domain-specific keyphrase extraction." KEA Proc. 16th International Joint Conference on Artificial Intelligence, Morgan Kaufmann Publishers, San Francisco, CA, pp. 668-673. [find](https://scholar.google.com/scholar?q=Frank+E%2C+Paynter+G%2EW%2E%2C+Witten+I%2EH%2E%2C+Gutwin+C%2E+and+Nevill%2DManning+C%2EG%2E+%281999%29+%22Domain%2Dspecific+keyphrase+extraction%2E%22+KEA+Proc%2E+16th+International+Joint+Conference+on+Artificial+Intelligence%2C+Morgan+Ka)
8. Goldstein, J., Kantrowitz, M., Mittal, V.O. and Carbonell, J.G., “Summarizing Text Documents: Sentence Selection and Evaluation Metrics”, in Pvoc. of SIGIR’99: the 22nd International Conference on Research and Development in Information Retrieval. Berkeley, CA, USA: ACM Press, 1999, pp. 121-128. [↗](https://doi.org/10.1184/r1/6610025)
9. Gong, Y. and Liu X.,(2001). Generic Text Summarization Using Relevance Measure and Latent Semantic Analysis. In Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, [find](https://scholar.google.com/scholar?q=Gong%2C+Y%2E+and+Liu+X%2E%2C%282001%29%2E+Generic+Text+Summarization+Using+Relevance+Measure+and+Latent+Semantic+Analysis%2E+In+Proceedings+of+the+24th+Annual+International+ACM+SIGIR+Conference+on+Research+and+Develo)
10. Hassel, Evaluation of Automatic Text Summarization - A practical implementation. Licentiate thesis, Department of Numerical Analysis and Computer Science, Royal Institute of Technology, Stockholm, Sweden, 2004. [find](https://scholar.google.com/scholar?q=Hassel%2C+Evaluation+of+Automatic+Text+Summarization+%2D+A+practical+implementation%2E+Licentiate+thesis%2C+Department+of+Numerical+Analysis+and+Computer+Science%2C+Royal+Institute+of+Technology%2C+Stockholm%2C+Swe)
11. Hovy, E. H. Automated Text Summarization. In R. Mitkov (ed), The Oxford Handbook of Computational Linguistics, chapter 32, pages 583-598.Oxford University Press, 2005. [find](https://scholar.google.com/scholar?q=Hovy%2C+E%2E+H%2E+Automated+Text+Summarization%2E+In+R%2E+Mitkov+%28ed%29%2C+The+Oxford+Handbook+of+Computational+Linguistics%2C+chapter+32%2C+pages+583%2D598%2EOxford+University+Press%2C+2005%2E)
12. Hovy, E.H. and Lin C. “Automated text summarization in SUMMARIST” In ACL/EACL summarization workshop, 18-24, Madrid, Spain, 1999. [find](https://scholar.google.com/scholar?q=Hovy%2C+E%2EH%2E+and+Lin+C%2E+%E2%80%9CAutomated+text+summarization+in+SUMMARIST%E2%80%9D+In+ACL%2FEACL+summarization+workshop%2C+18%2D24%2C+Madrid%2C+Spain%2C+1999%2E)
13. Lin, C. “Training a Selection Function for Extraction” in Pvoc. of the 8th International Conference on Knowledge Management. Kansas City, MO USA: ACM Press, 1999, [find](https://scholar.google.com/scholar?q=Lin%2C+C%2E+%E2%80%9CTraining+a+Selection+Function+for+Extraction%E2%80%9D+in+Pvoc%2E+of+the+8th+International+Conference+on+Knowledge+Management%2E+Kansas+City%2C+MO+USA%3A+ACM+Press%2C+1999%2C)
14. Luhn, H.. “The automatic Creation of Literature Abstracts”, IBM Journal of Research and Development 2(92):, 1958.. [↗](https://doi.org/10.1147/rd.22.0159)
15. Morris, J., and Hirst, G.. [Lexical cohesion computed by thesaural relations as an indicator of the structure of text](https://md.research.elamur.ai/free/en/papers/morris-1991-lexical-cohesion-computed-thesaural-relations/). Computational Linguistics 17(1), 1991.
16. Padro Cirera, L., Fuentes, M.J., Alonso, L., et al. Approaches to Text Summarization: Questions and Answers. Revista beroamericana de Inteligencia Artificial, ISSN 1137-3601, 2004. [find](https://scholar.google.com/scholar?q=Padro+Cirera%2C+L%2E%2C+Fuentes%2C+M%2EJ%2E%2C+Alonso%2C+L%2E%2C+et+al%2E+Approaches+to+Text+Summarization%3A+Questions+and+Answers%2E+Revista+beroamericana+de+Inteligencia+Artificial%2C+ISSN+1137%2D3601%2C+2004%2E)
17. Rafeeq Al-Hashemi, Text Summarization Extraction System (TSES) Using Extracted Keywords, International Arab Journal of e-Technology, Vol. 1, No. 4, June 2010. [find](https://scholar.google.com/scholar?q=Rafeeq+Al%2DHashemi%2C+Text+Summarization+Extraction+System+%28TSES%29+Using+Extracted+Keywords%2C+International+Arab+Journal+of+e%2DTechnology%2C+Vol%2E+1%2C+No%2E+4%2C+June+2010%2E)
18. Sobh, I., Darwish, N., Fayek. M. (2007). "An Optimized Dual Classification System for Arabic Extractive Generic Text Summarization" in proceedings of the Seventh Conference on Language Engineering, ESLEC. [http://www.RDI-eg.com/RDI/Technologies/paper.htm](http://www.RDI-eg.com/RDI/Technologies/paper.htm) [↗](http://www.RDI-eg.com/RDI/Technologies/paper.htm)
19. Salton, G., A. Singhal, M. Mitra, and C. Buckley. ‘Automatic text structuring and summarization, Information Processing and Management 33(2), 1997. [find](https://scholar.google.com/scholar?q=Salton%2C+G%2E%2C+A%2E+Singhal%2C+M%2E+Mitra%2C+and+C%2E+Buckley%2E+%E2%80%98Automatic+text+structuring+and+summarization%2C+Information+Processing+and+Management+33%282%29%2C+1997%2E)
20. Steve J, Lundy S, Paynter W, "Interactive Document Summarisation Using Automatically Extracted Keyphrases," Proceedings of the 35th Hawaii International Conference on System Sciences – 2002. [find](https://scholar.google.com/scholar?q=Steve+J%2C+Lundy+S%2C+Paynter+W%2C+%22Interactive+Document+Summarisation+Using+Automatically+Extracted+Keyphrases%2C%22+Proceedings+of+the+35th+Hawaii+International+Conference+on+System+Sciences+%E2%80%93+2002%2E)
21. Turney, P.D. "Learning Algorithms for Keyphrase Extraction", Information Retrieval, 2(4), 303-336 (National Research Council 44105, Canada, 2000. [↗](https://doi.org/10.1023/a:1009976227802)
22. Turney, P.D.. Mining the Web for Lexical Knowledge to Improve Keyphrase Extraction: Learning from labeled and Unlabeled Data. National Research Council, Institute for Information Technology, Canada. Technical Report ERB-1096, 2002. [find](https://scholar.google.com/scholar?q=Turney%2C+P%2ED%2E%2E+Mining+the+Web+for+Lexical+Knowledge+to+Improve+Keyphrase+Extraction%3A+Learning+from+labeled+and+Unlabeled+Data%2E+National+Research+Council%2C+Institute+for+Information+Technology%2C+Canada%2E+T)
23. UNICEF, "2011 UNICEF Humanitarian Action for Children building resilience", available at [http://www.unicef.org/hac2011/](http://www.unicef.org/hac2011/) [↗](http://www.unicef.org/hac2011/)
24. Yatani K, Novati M, Trusty A, and Khai N. Truong, "Analysis of Adjective-Noun Word Pair Extraction Methods for Online Review Summarization," Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, 2011. Tarek El-Shishtawy is a Professor assistant at Faculty of Engineering, Benha University, Egypt. He participated in many Arabic computational Linguistic projects. Large Scale Arabic annotated Corpus, 1995, was one of important projects for Egyptian Computer Society, and Academy of Scientific Research and Technology, He has many publications in Arabic Corpus, machine translation, Text, and data Mining. Fatma El-Ghannam is a researcher assistance at Electronics Research Institute – Cairo, Egypt. She has great research interests in Arabic language generation and analysis. Currently, she's preparing for a Ph.D. degree in NLP. [find](https://scholar.google.com/scholar?q=Yatani+K%2C+Novati+M%2C+Trusty+A%2C+and+Khai+N%2E+Truong%2C+%22Analysis+of+Adjective%2DNoun+Word+Pair+Extraction+Methods+for+Online+Review+Summarization%2C%22+Proceedings+of+the+Twenty%2DSecond+International+Joint+Confer)

*Updated 1 November 2026*