---
title: "Al-Bayan: A Knowledge-based System for Arabic Answer Selection"
description: "The paper tackles answer selection for Arabic community QA in SemEval-2015… 74.53% accuracy. 17 references, cited by 5 papers here."
authors: ["Reham Mohamed", "Maha Ragab", "Heba Abdelnasser", "Nagwa M. El-Makky", "Marwan Torki"]
year: 2015
venue: "Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)"
source: "https://aclanthology.org/S15-2040/"
doi: "10.18653/v1/s15-2040"
licence: "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)"
licence_url: "https://creativecommons.org/licenses/by-nc-sa/3.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/mohamed-2015-al-bayan-knowledge-based-system/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mohamed-2015-al-bayan-knowledge-based-system/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2015](https://md.research.elamur.ai/free/en/papers/2015/page/3/) / Al-Bayan: A Knowledge-based System for Arabic Answer Selection

# Al-Bayan: A Knowledge-based System for Arabic Answer Selection

**Authors:** [Reham Mohamed](https://md.research.elamur.ai/free/en/authors/reham-mohamed/), [Maha Ragab](https://md.research.elamur.ai/free/en/authors/maha-ragab/), [Heba Abdelnasser](https://md.research.elamur.ai/free/en/authors/heba-abdelnasser/), Nagwa M. El-Makky and [Marwan Torki](https://md.research.elamur.ai/free/en/authors/marwan-torki/) · **Year:** 2015 · **Venue:** [Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)](https://md.research.elamur.ai/free/en/venues/semeval/) ([SemEval 2015](https://md.research.elamur.ai/free/en/venues/semeval/2015/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY-NC-SA 3.0 (ACL Anthology, before 2016)](https://creativecommons.org/licenses/by-nc-sa/3.0/)

**Links:** [Publisher's page](https://aclanthology.org/S15-2040/) · [PDF](https://aclanthology.org/S15-2040.pdf) · [DOI 10.18653/v1/s15-2040](https://doi.org/10.18653/v1/s15-2040) · [OpenAlex](https://openalex.org/W2250877322)

**Citations:** 16 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/mohamed-2015-al-bayan-knowledge-based-system/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper tackles answer selection for Arabic community QA in SemEval-2015 Task 3, Subtask A. Questions come from the Fatwa website on Islamic topics, and each candidate answer must be labeled Direct, Related or Irrelevant. The authors' system relies on a domain knowledge resource rather than generic text features. They merged two existing Quranic ontologies (Quranic Corpus Ontology and Qurany), corrected them by hand, and attached every Quran verse plus two classical Tafseer commentaries to the leaf concepts. From these concept documents they built an Explicit Semantic Analysis interpreter that maps any text to a TF-IDF-weighted vector of concepts. Question and answer vectors are then compared by cosine similarity. A normalized keyword overlap score is added, and both features go into a decision tree. On the official test set the system reached 74.53% accuracy and 67.65% macro-F1, in the range of other participants. The work shows that a curated, domain-specific concept inventory can provide useful semantic signal in a narrow-domain CQA setting.

## Key points
- Preprocessing uses MADA for morphology. Terms are kept as stem + POS in Buckwalter transliteration, and stopwords are removed by POS (pronouns, prepositions, conjunctions and similar).
- The ontology integrates the Quranic Corpus Ontology and the Qurany Ontology, with about 1,200 concepts revised by hand. The result has 1217 leaf concepts covering all 6236 verses. The 621 verses left unassigned after merging were placed via a verse-similarity module.
- Concept documents combine verses with the Tafseer of Ibn-Kathir and Al-Jaza'iri. They are indexed with Lucene using TF-IDF weights, and a text's vector is the mean of its terms' concept vectors.
- The dataset has 1300 training questions with 6500 answers and 200 test questions with 1001 answers, five answers per question.
- Test results: accuracy 74.53%, macro-F1 67.65%. The Related class is weakest (F 0.467) and Irrelevant is strongest (F 0.854). Related is confused heavily with both neighbouring classes.

## Interesting ideas
- Represent a term by the concepts whose attached documents mention it, turning a hand-built ontology into an interpretable concept-space where each dimension is a named concept.
- Close coverage gaps in a resource by assigning unlabeled items to the concept of their most similar already-labeled items, then keep the result for review.
- Normalize the keyword score per question across all of its candidate answers, so features measure relative standing among competitors rather than absolute counts.
- Filter function words by POS tag instead of a fixed word list, which adapts naturally to a morphologically rich language.
- Report the full confusion matrix for a graded label scale, which exposes that the middle "partly relevant" class leaks into both extremes.

## For Mova

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

- **I1** (world): Concept glosses and examples from WordNet/FrameNet could be indexed to give each word a ranked list of candidate ontology nodes, as an explainable prior when linking entities to the knowledge graph.
- **I2** (learn): Verbs or lemmas missing from VerbNet classes could get provisional classes from their nearest classified neighbours, marked as silver until confirmed by other witnesses.
- **I3** (answer): In school-test multiple choice, option scores could be rescaled within each question before deciding, so long or wordy options are not favoured automatically.
- **I4** (tokens): Content/function masks could come straight from the en tagger's UPOS, keeping one consistent definition for downstream matching.
- **I5** (answer): QA evaluation could include partial-answer labels and check confusion with the matrix, to see whether failures are near-misses or outright wrong readings.

*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

- [Alexandria University](https://md.research.elamur.ai/free/en/universities/alexandria-university/) — University, Alexandria, Egypt · 39 works · 287 citations

📚 Shelves (5): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (2): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works

## Cite

Cite as: Reham Mohamed, Maha Ragab, Heba Abdelnasser, Nagwa M. El-Makky and Marwan Torki. 2015. Al-Bayan: A Knowledge-based System for Arabic Answer Selection. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015).

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

```bibtex
@inproceedings{mohamed2015al,
  title = {{Al-Bayan: A Knowledge-based System for Arabic Answer Selection}},
  author = {Reham Mohamed, Maha Ragab, Heba Abdelnasser, Nagwa M. El-Makky and Marwan Torki},
  booktitle = {Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)},
  year = {2015},
  doi = {10.18653/v1/s15-2040},
  url = {https://doi.org/10.18653/v1/s15-2040}
}
```

- [← previous Using Word Semantics To Assist English as a Second Language Learners](https://md.research.elamur.ai/free/en/papers/azab-2015-word-semantics-assist-english-as/)
- [next → Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers](https://md.research.elamur.ai/free/en/papers/chen-2015-chinese-event-coreference-resolution-unsupervised/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/page/3/)

## References

17 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdul-Baquee M. Sharaf and Eric Atwell. 2012. [QurAna: Corpus of the Quran annotated with Pronominal Anaphora](https://md.research.elamur.ai/free/en/papers/sharaf-2012-qurana-corpus-quran-annotated-pronominal/). LREC.
2. Abdul-Baquee M. Sharaf and Eric Atwell. 2012. QurSim: A corpus for evaluation of relatedness in short texts. LREC. [↗](https://doi.org/10.13140/2.1.4007.0088)
3. Abu Bakr Al-Jaza’iri. 1986. Aysar al-Tafasir li Kalaam il ’Aliyy il Kabir. [find](https://scholar.google.com/scholar?q=Abu+Bakr+Al%2DJaza%E2%80%99iri%2E+1986%2E+Aysar+al%2DTafasir+li+Kalaam+il+%E2%80%99Aliyy+il+Kabir%2E)
4. Ahmed Magdy Ezzeldin, Mohamed Hamed Kholief, and Yasser El-Sonbaty. 2013. ALQASIM: Arabic language question answer selection in machines. In Information Access Evaluation. Multilinguality, Multimodality, and Visualization, Springer, Berlin Heidelberg. [find](https://scholar.google.com/scholar?q=Ahmed+Magdy+Ezzeldin%2C+Mohamed+Hamed+Kholief%2C+and+Yasser+El%2DSonbaty%2E+2013%2E+ALQASIM%3A+Arabic+language+question+answer+selection+in+machines%2E+In+Information+Access+Evaluation%2E+Multilinguality%2C+Multimodali)
5. Eric Atwell, Claire Brierley, Kais Dukes, Majdi Sawalha and Abdul-Baquee Sharaf. 2011. A An Artificial Intelligence Approach to Arabic and Islamic Content on the Internet. Proceedings of NITS 3rd National Information Technology Symposium. [find](https://scholar.google.com/scholar?q=Eric+Atwell%2C+Claire+Brierley%2C+Kais+Dukes%2C+Majdi+Sawalha+and+Abdul%2DBaquee+Sharaf%2E+2011%2E+A+An+Artificial+Intelligence+Approach+to+Arabic+and+Islamic+Content+on+the+Internet%2E+Proceedings+of+NITS+3rd+Nati)
6. Evgeniy Gabrilovich and Shaul Markovitch. 2007. Computing Semantic Relatedness Using Wikipedia-based Explicit Semantic Analysis, volume 7. Proceedings of the 20th international joint conference on artificial intelligence. [find](https://scholar.google.com/scholar?q=Evgeniy+Gabrilovich+and+Shaul+Markovitch%2E+2007%2E+Computing+Semantic+Relatedness+Using+Wikipedia%2Dbased+Explicit+Semantic+Analysis%2C+volume+7%2E+Proceedings+of+the+20th+international+joint+conference+on+art)
7. Heba Abdelnasser, Reham Mohamed, Maha Ragab, Alaa Mohamed, Bassant Farouk, Nagwa El-Makky, and Marwan Torki. 2014. [Al-Bayan: An Arabic Question Answering System for the Holy Quran](https://md.research.elamur.ai/free/en/papers/abdelnasser-2014-al-bayan-arabic-question-answering/). Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP). [↗](https://doi.org/10.13140/2.1.4113.4400)
8. Hikmat Ullah Khan and Syed Muhammad Saqlain and Muhammad Shoaib and Muhammad Sher. 2013. Ontology Based Semantic Search in Holy Quran., volume 2. International Journal of Future Computer and Communication, 570-575. Ismail Ibn-Kathir. 1370. Tafsir al-Qur’an al-Azim. [find](https://scholar.google.com/scholar?q=Hikmat+Ullah+Khan+and+Syed+Muhammad+Saqlain+and+Muhammad+Shoaib+and+Muhammad+Sher%2E+2013%2E+Ontology+Based+Semantic+Search+in+Holy+Quran%2E%2C+volume+2%2E+International+Journal+of+Future+Computer+and+Communica)
9. Lahsen Abouenour, Karim Bouzoubaa, and Paolo Rosso. 2012. IDRAAQ: New Arabic Question Answering System Based on Query Expansion and Passage Retrieval. In CLEF. [find](https://scholar.google.com/scholar?q=Lahsen+Abouenour%2C+Karim+Bouzoubaa%2C+and+Paolo+Rosso%2E+2012%2E+IDRAAQ%3A+New+Arabic+Question+Answering+System+Based+on+Query+Expansion+and+Passage+Retrieval%2E+In+CLEF%2E)
10. Lluı̀s Màrquez and James Glass and Walid Magdy and Alessandro Moschitti and Preslav Nakov and Bilal Randeree. 2015. SemEval-2015 Task 3: Answer Selection in Community Question Answering. Proceedings of the 9th International Workshop on Semantic Evaluation. [find](https://scholar.google.com/scholar?q=Llu%C4%B1%CC%80s+Ma%CC%80rquez+and+James+Glass+and+Walid+Magdy+and+Alessandro+Moschitti+and+Preslav+Nakov+and+Bilal+Randeree%2E+2015%2E+SemEval%2D2015+Task+3%3A+Answer+Selection+in+Community+Question+Answering%2E+Proceedings+)
11. Manal AlMaayah, Majdi Sawalha, and Mohammad AM Abushariah. 2014. A Proposed Model for Quranic Arabic WordNet. LRE-REL2, 9. [find](https://scholar.google.com/scholar?q=Manal+AlMaayah%2C+Majdi+Sawalha%2C+and+Mohammad+AM+Abushariah%2E+2014%2E+A+Proposed+Model+for+Quranic+Arabic+WordNet%2E+LRE%2DREL2%2C+9%2E)
12. Nizar Habash, Owen Rambow and Ryan Roth. 2009. MADA+ TOKAN: A toolkit for Arabic tokenization, diacritization, morphological disambiguation, POS tagging, stemming and lemmatization. Proceedings of the 2nd International Conference on Arabic Language Resources and Tools (MEDAR), Cairo, Egypt. [find](https://scholar.google.com/scholar?q=Nizar+Habash%2C+Owen+Rambow+and+Ryan+Roth%2E+2009%2E+MADA%2B+TOKAN%3A+A+toolkit+for+Arabic+tokenization%2C+diacritization%2C+morphological+disambiguation%2C+POS+tagging%2C+stemming+and+lemmatization%2E+Proceedings+of+the)
13. Noorhan Hassan Abbas. 2009. Quran’search for a Concept’Tool and Website. M. Sc. thesis, University of Leeds (School of Computing). [find](https://scholar.google.com/scholar?q=Noorhan+Hassan+Abbas%2E+2009%2E+Quran%E2%80%99search+for+a+Concept%E2%80%99Tool+and+Website%2E+M%2E+Sc%2E+thesis%2C+University+of+Leeds+%28School+of+Computing%29%2E)
14. Omar Trigui, Lamia Hadrich Belguith, Paolo Rosso, Hichem Ben Amor and Bilel Gafsaoui. 2012. Arabic QA4MRE at CLEF 2012: Arabic Question Answering for Machine Reading Evaluation. CLEF (Online Working Notes/Labs/Workshop). [find](https://scholar.google.com/scholar?q=Omar+Trigui%2C+Lamia+Hadrich+Belguith%2C+Paolo+Rosso%2C+Hichem+Ben+Amor+and+Bilel+Gafsaoui%2E+2012%2E+Arabic+QA4MRE+at+CLEF+2012%3A+Arabic+Question+Answering+for+Machine+Reading+Evaluation%2E+CLEF+%28Online+Working+N)
15. Saidah Saad, Naomie Salim, and Hakim Zainal. 2009. Pattern extraction for Islamic concept., volume 2. Proceedings of IEEE 2nd. International Conference on Electrical Engineering & Informatics (ICEEI). [find](https://scholar.google.com/scholar?q=Saidah+Saad%2C+Naomie+Salim%2C+and+Hakim+Zainal%2E+2009%2E+Pattern+extraction+for+Islamic+concept%2E%2C+volume+2%2E+Proceedings+of+IEEE+2nd%2E+International+Conference+on+Electrical+Engineering+%26+Informatics+%28ICEEI%29%2E)
16. Saidah Saad, Naomie Salim, Hakim Zainal and S. Azman M. Noah. 2010. A framework for Islamic knowledge via ontology representation.. International Conference on Information Retrieval and Knowledge Management (CAMP). [find](https://scholar.google.com/scholar?q=Saidah+Saad%2C+Naomie+Salim%2C+Hakim+Zainal+and+S%2E+Azman+M%2E+Noah%2E+2010%2E+A+framework+for+Islamic+knowledge+via+ontology+representation%2E%2E+International+Conference+on+Information+Retrieval+and+Knowledge+Mana)
17. Tim Buckwalter. 2002. Arabic transliteration. URL [http://www.qamus.org/transliteration.htm](http://www.qamus.org/transliteration.htm). [↗](http://www.qamus.org/transliteration.htm)

*Updated 1 November 2026*