---
title: "EDRAK: Entity-Centric Data Resource for Arabic Knowledge (2015)"
description: "Arabic NLP tools such as named entity disambiguation and dictionary-based NER perform poorly because there are few… 26 references."
authors: ["Mohamed H. Gad-Elrab", "Mohamed Amir Yosef", "Gerhard Weikum"]
year: 2015
venue: "Proceedings of the Second Workshop on Arabic Natural Language Processing"
source: "https://aclanthology.org/W15-3224/"
doi: "10.18653/v1/w15-3224"
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/elrab-2015-edrak-entity-centric-data-resource/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/elrab-2015-edrak-entity-centric-data-resource/)

[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/4/) / EDRAK: Entity-Centric Data Resource for Arabic Knowledge

# EDRAK: Entity-Centric Data Resource for Arabic Knowledge

**Authors:** Mohamed H. Gad-Elrab, [Mohamed Amir Yosef](https://md.research.elamur.ai/free/en/authors/mohamed-amir-yosef/) and [Gerhard Weikum](https://md.research.elamur.ai/free/en/authors/gerhard-weikum/) · **Year:** 2015 · **Venue:** [Proceedings of the Second Workshop on Arabic Natural Language Processing](https://md.research.elamur.ai/free/en/venues/workshop-on-arabic-natural-language-processing/) ([Workshop on Arabic Natural Language Processing 2015](https://md.research.elamur.ai/free/en/venues/workshop-on-arabic-natural-language-processing/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/W15-3224/) · [PDF](https://aclanthology.org/W15-3224.pdf) · [DOI 10.18653/v1/w15-3224](https://doi.org/10.18653/v1/w15-3224) · [OpenAlex](https://openalex.org/W2250865411)

**Citations:** 2 citations (OpenAlex, 2026-10-14)

## Summary
Arabic NLP tools such as named entity disambiguation and dictionary-based NER perform poorly because there are few structured Arabic resources. Arabic Wikipedia is roughly ten times smaller than the English one, and its infoboxes are less complete. EDRAK addresses this gap with an automatically built entity resource. It starts from a YAGO3 entity catalogue compiled from both Wikipedias and attaches Arabic names and weighted contextual keyphrases to each entity. Arabic Wikipedia material (titles, redirects, anchors, categories, linking pages) is kept unchanged. English-only material is converted to Arabic in three ways:
- names are borrowed from external dictionaries such as GW2C when they link to the same entity;
- phrase-based SMT is trained on parallel English-Arabic name lists;
- a character-level SMT transliterator handles person names.

The final resource covers about 2.4M entities. Fifty-five native speakers judged the top candidate translations, and the quality varied by source. Short person names scored well, while long redirects and categories were noticeably worse. The resource is public and can support NED, entity typing, relatedness and summarization.

## Key points
- About 2.4M entities, typed under the YAGO hierarchy. They are built from the English dump of 12 Jan 2015 and the Arabic dump of 18 Dec 2014. YAGO was chosen for its emphasis on precision.
- GW2C is noisy, so it was filtered with language detection, which left only 736K Arabic entries out of 297M. Ambiguous names were then removed using the resource's own conditional probability scores.
- Arabic text was preprocessed with the Stanford Arabic Word Segmenter: clitics were split, and Tatweel, digits, Alif and diacritics were normalized. Translation and transliteration were done with cdec.
- The evaluation covered 1646 English surface forms and 4463 candidate Arabic forms. Each item was judged by three people, and Fleiss' kappa was 0.484 (moderate agreement).
- Top-1 precision was strongest for person-name sources: First Name 87.5–100%, Last Name 87.5–92.9%, rdfs:label about 80%. Non-person rdfs:label reached about 50–53%, non-person redirects about 46%, and categories 67.8%. Person-name transliteration did worse than translation.

## Interesting ideas
- Two names, from the same or different dictionaries, count as translations of each other when both point to the same canonical entity, so the entity acts as the pivot instead of raw string alignment
- A large noisy web dictionary becomes usable by first filtering by language and then dropping mappings whose conditional probability of the entity given the string is low
- Separate translation models for persons and non-persons gave no clear gain over one shared model, a useful negative result before splitting systems by type
- Quality was reported per data source (labels, redirects, first/last names, categories), and samples followed the real source distribution, which exposed redirects as a weak source because they are often not true names
- Judges picked all acceptable options among the top-K candidates, and precision was reported at K=1,2,3, which shows how much quality is lost by keeping more alternatives

## For Mova

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

- **I1** (world): Names from Wikidata/WordNet sources could be merged into one alias table per entity ID, so different surface forms resolve to the same world entity without guessing from strings.
- **I2** (world): The same two-step filter could clean bulk alias or gazetteer imports before they enter the knowledge graph, keeping only links that name the entity with high probability.
- **I3** (learn): Before training type-specific variants of a component, compare them against a single universal model on the same held-out set and keep the split only if it clearly wins.
- **I4** (learn): Silver data should be scored per provenance channel, so that a weak source can be down-weighted or dropped instead of being hidden in an overall average.
- **I5** (answer): When a reader keeps several candidate entity readings, precision at each depth tells how many alternatives can be kept before noise outweighs recall.

*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

- [Max Planck Institute for Informatics](https://md.research.elamur.ai/free/en/labs/max-planck-institute-for-informatics/) — Research institute, Saarbrücken, Germany · 18 works · 4,545 citations

📚 Shelves (4): [🖥️ 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works

## Cite

Cite as: Mohamed H. Gad-Elrab, Mohamed Amir Yosef and Gerhard Weikum. 2015. EDRAK: Entity-Centric Data Resource for Arabic Knowledge. Proceedings of the Second Workshop on Arabic Natural Language Processing.

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

```bibtex
@inproceedings{gadelrab2015edrak,
  title = {{EDRAK: Entity-Centric Data Resource for Arabic Knowledge}},
  author = {Mohamed H. Gad-Elrab, Mohamed Amir Yosef and Gerhard Weikum},
  booktitle = {Proceedings of the Second Workshop on Arabic Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/w15-3224},
  url = {https://doi.org/10.18653/v1/w15-3224}
}
```

- [← previous Developing instructional materials of English morphology for English department college-learners](https://md.research.elamur.ai/free/en/papers/umam-2015-developing-instructional-materials-english-morphology/)
- [next → Polysemy in specialized lexicon from Old English to Present-Day English](https://md.research.elamur.ai/free/en/papers/iglesias-2015-polysemy-specialized-lexicon-old-english/)
- [↑ back to papers of 2015](https://md.research.elamur.ai/free/en/papers/2015/page/4/)

## References

26 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Mohamed Al-Badrashiny, Ramy Eskander, Nizar Habash, and Owen Rambow. 2014. [Automatic Transliteration of Romanized Dialectal Arabic](https://md.research.elamur.ai/free/en/papers/badrashiny-2014-automatic-transliteration-romanized-dialectal-arabic/). In Proceedings of the 18th Conference on Computational Natural Language Learning, CoNLL 2014, Baltimore, Maryland, USA.
2. Yaser Al-Onaizan and Kevin Knight. 2002. [Translating Named Entities Using Monolingual and Bilingual Resources](https://md.research.elamur.ai/free/en/papers/onaizan-2002-translating-named-entities-monolingual-bilingual/). In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL 2002, Stroudsburg, PA, USA.
3. Mohammed Attia, Antonio Toral, Lamia Tounsi, Monica Monachini, and Josef van Genabith. 2010. [An Automatically Built Named Entity Lexicon for Arabic](https://md.research.elamur.ai/free/en/papers/attia-2010-automatically-built-named-entity-lexicon/). In Proceedings of the 7th International Conference on Language Resources and Evaluation, LREC 2010, Valletta, Malta.
4. Sren Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, and Zachary Ives. 2007. DBpedia: A Nucleus for a Web of Open Data. In Proceedings of the 6th International Semantic Web Conference, ISWC 2007, Busan, Korea. [find](https://scholar.google.com/scholar?q=Sren+Auer%2C+Christian+Bizer%2C+Georgi+Kobilarov%2C+Jens+Lehmann%2C+and+Zachary+Ives%2E+2007%2E+DBpedia%3A+A+Nucleus+for+a+Web+of+Open+Data%2E+In+Proceedings+of+the+6th+International+Semantic+Web+Conference%2C+ISWC+200)
5. Mahmoud Azab, Houda Bouamor, Behrang Mohit, and Kemal Oflazer. 2013. [Dudley North visits North London: Learning When to Transliterate to Arabic](https://md.research.elamur.ai/free/en/papers/azab-2013-dudley-north-visits-north-london/). In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAAC-HLT 2013, Atlanta, Georgia.
6. William Black, Sabri Elkateb, and Piek Vossen. 2006. Introducing the Arabic Wordnet Project. In In Proceedings of the 3rd International WordNet Conference, GWC 2006, Jeju Island. Korea. [find](https://scholar.google.com/scholar?q=William+Black%2C+Sabri+Elkateb%2C+and+Piek+Vossen%2E+2006%2E+Introducing+the+Arabic+Wordnet+Project%2E+In+In+Proceedings+of+the+3rd+International+WordNet+Conference%2C+GWC+2006%2C+Jeju+Island%2E+Korea%2E)
7. Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: A Collaboratively created Graph Database for Structuring Human Knowledge. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD 2008, New York, NY, USA. [find](https://scholar.google.com/scholar?q=Kurt+Bollacker%2C+Colin+Evans%2C+Praveen+Paritosh%2C+Tim+Sturge%2C+and+Jamie+Taylor%2E+2008%2E+Freebase%3A+A+Collaboratively+created+Graph+Database+for+Structuring+Human+Knowledge%2E+In+Proceedings+of+the+2008+ACM+SI)
8. Kareem Darwish. 2013. [Named Entity Recognition Using Cross-lingual Resources: Arabic as an Example](https://md.research.elamur.ai/free/en/papers/darwish-2013-named-entity-recognition-cross-lingual/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, Sofia, Bulgaria.
9. Chris Dyer, Adam Lopez, Juri Ganitkevitch, Johnathan Weese, Ferhan Ture, Phil Blunsom, Hendra Setiawan, Vladimir Eidelman, and Philip Resnik. 2010. [cdec: A Decoder, Alignment, and Learning Framework for Finite-state and Context-free Translation Models](https://md.research.elamur.ai/free/en/papers/dyer-2010-cdec-decoder-alignment-learning-framework/). In Proceedings of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden.
10. Ondrej Hálek, Rudolf Rosa, Ales Tamchyna, and Ondrej Bojar. 2011. Named Entities from Wikipedia for Machine Translation. In Proceedings of the Conference on Theory and Practice of Information Technologies, ITAT 2010, Velká Fatra, Slovak Republic. [find](https://scholar.google.com/scholar?q=Ondrej+Ha%CC%81lek%2C+Rudolf+Rosa%2C+Ales+Tamchyna%2C+and+Ondrej+Bojar%2E+2011%2E+Named+Entities+from+Wikipedia+for+Machine+Translation%2E+In+Proceedings+of+the+Conference+on+Theory+and+Practice+of+Information+Technol)
11. Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bordino, Hagen Fürstenau, Manfred Pinkal, Marc Spaniol, Bilyana Taneva, Stefan Thater, and Gerhard Weikum. 2011. Robust Disambiguation of Named Entities in Text. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, Edinburgh, UK. [find](https://scholar.google.com/scholar?q=Johannes+Hoffart%2C+Mohamed+Amir+Yosef%2C+Ilaria+Bordino%2C+Hagen+Fu%CC%88rstenau%2C+Manfred+Pinkal%2C+Marc+Spaniol%2C+Bilyana+Taneva%2C+Stefan+Thater%2C+and+Gerhard+Weikum%2E+2011%2E+Robust+Disambiguation+of+Named+Entities+i)
12. Johannes Hoffart, Stephan Seufert, Dat Ba Nguyen, Martin Theobald, and Gerhard Weikum. 2012. KORE: Keyphrase Overlap Relatedness for Entity Disambiguation. In Proceedings of the 21st ACM International Conference on Information and Knowledge Management, CIKM 2012, Hawaii, USA. [find](https://scholar.google.com/scholar?q=Johannes+Hoffart%2C+Stephan+Seufert%2C+Dat+Ba+Nguyen%2C+Martin+Theobald%2C+and+Gerhard+Weikum%2E+2012%2E+KORE%3A+Keyphrase+Overlap+Relatedness+for+Entity+Disambiguation%2E+In+Proceedings+of+the+21st+ACM+International)
13. Johannes Hoffart, Fabian M. Suchanek, Klaus Berberich, and Gerhard Weikum. 2013. YAGO2: A Spatially and Temporally Enhanced Knowledge Base from Wikipedia. Journal of Artificial Intelligence. [↗](https://doi.org/10.1016/j.artint.2012.06.001)
14. Farzaneh Mahdisoltani, Joanna Biega, and Fabian M Suchanek. 2015. [Yago3: A Knowledge Base from Multilingual Wikipedias](https://md.research.elamur.ai/free/en/papers/mahdisoltani-2015-yago3-knowledge-base-multilingual-wikipedias/).
15. Will Monroe, Spence Green, and Christopher D. Manning. 2014. [Word Segmentation of Informal Arabic with Domain Adaptation](https://md.research.elamur.ai/free/en/papers/monroe-2014-word-segmentation-informal-arabic-domain/). In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014, Baltimore, MD, USA.
16. Roberto Navigli and Simone Paolo Ponzetto. 2012. BabelNet: The Automatic Construction, Evaluation and Application of a Wide-coverage Multilingual Semantic Network. Journal of Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Roberto+Navigli+and+Simone+Paolo+Ponzetto%2E+2012%2E+BabelNet%3A+The+Automatic+Construction%2C+Evaluation+and+Application+of+a+Wide%2Dcoverage+Multilingual+Semantic+Network%2E+Journal+of+Artificial+Intelligence%2E)
17. Arfath Pasha, Mohamed Al-Badrashiny, Mona Diab, Ahmed El Kholy, Ramy Eskander, Nizar Habash, Manoj Pooleery, Owen Rambow, and Ryan M Roth. 2014. [MADAMIRA: A Fast, Comprehensive Tool for Morphological Analysis and Disambiguation of Arabic](https://md.research.elamur.ai/free/en/papers/pasha-2014-madamira-fast-comprehensive-tool-morphological/). Proceedings of the Language Resources and Evaluation Conference, LREC 2014, Reykjavik, Iceland.
18. Khaled Shaalan. 2014. [A Survey of Arabic Named Entity Recognition and Classification](https://md.research.elamur.ai/free/en/papers/shaalan-2014-survey-arabic-named-entity-recognition/). Computational Linguistics. [↗](https://doi.org/10.1162/coli_a_00178)
19. Nakatani Shuyo. 2010. Language Detection Library for Java. [find](https://scholar.google.com/scholar?q=Nakatani+Shuyo%2E+2010%2E+Language+Detection+Library+for+Java%2E)
20. Valentin I. Spitkovsky and Angel X. Chang. 2012. A Cross-lingual Dictionary for English Wikipedia Concepts. In Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012, Istanbul, Turkey. [find](https://scholar.google.com/scholar?q=Valentin+I%2E+Spitkovsky+and+Angel+X%2E+Chang%2E+2012%2E+A+Cross%2Dlingual+Dictionary+for+English+Wikipedia+Concepts%2E+In+Proceedings+of+the+8th+International+Conference+on+Language+Resources+and+Evaluation%2C+LRE)
21. Ralf Steinberger, Bruno Pouliquen, Mijail Kabadjov, Jenya Belyaeva, and Erik van der Goot. 2011. JRC-NAMES: A Freely Available, Highly Multilingual Named Entity Resource. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2011, Hissar, Bulgaria. [find](https://scholar.google.com/scholar?q=Ralf+Steinberger%2C+Bruno+Pouliquen%2C+Mijail+Kabadjov%2C+Jenya+Belyaeva%2C+and+Erik+van+der+Goot%2E+2011%2E+JRC%2DNAMES%3A+A+Freely+Available%2C+Highly+Multilingual+Named+Entity+Resource%2E+In+Proceedings+of+the+Interna)
22. Tomasz Tylenda, Mauro Sozio, and Gerhard Weikum. 2011. Einstein: Physicist or Vegetarian? Summarizing Semantic Type Graphs for Knowledge Discovery. In Proceedings of the 20th International Conference on World Wide Web, WWW 2011, Hyderabad, India. [find](https://scholar.google.com/scholar?q=Tomasz+Tylenda%2C+Mauro+Sozio%2C+and+Gerhard+Weikum%2E+2011%2E+Einstein%3A+Physicist+or+Vegetarian%3F+Summarizing+Semantic+Type+Graphs+for+Knowledge+Discovery%2E+In+Proceedings+of+the+20th+International+Conference+)
23. Gerhard Weikum, Johannes Hoffart, Ndapandula Nakashole, Marc Spaniol, Fabian M Suchanek, and Mohamed Amir Yosef. 2012. Big Data Methods for Computational Linguistics. IEEE Data Engineering Bulletin. [find](https://scholar.google.com/scholar?q=Gerhard+Weikum%2C+Johannes+Hoffart%2C+Ndapandula+Nakashole%2C+Marc+Spaniol%2C+Fabian+M+Suchanek%2C+and+Mohamed+Amir+Yosef%2E+2012%2E+Big+Data+Methods+for+Computational+Linguistics%2E+IEEE+Data+Engineering+Bulletin%2E)
24. Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart Marc Spaniol, and Gerhard Weikum. 2012. HYENA: Hierarchical Type Classification for Entity Names. In Proc. of the 24th International Conference on Computational Linguistics, COLING 2012, Mumbai, India. [find](https://scholar.google.com/scholar?q=Mohamed+Amir+Yosef%2C+Sandro+Bauer%2C+Johannes+Hoffart+Marc+Spaniol%2C+and+Gerhard+Weikum%2E+2012%2E+HYENA%3A+Hierarchical+Type+Classification+for+Entity+Names%2E+In+Proc%2E+of+the+24th+International+Conference+on+Co)
25. Mohamed Amir Yosef, Sandro Bauer, Johannes Hoffart Marc Spaniol, and Gerhard Weikum. 2013. HYENA-live: Fine-Grained Online Entity Type Classification from Natural-language Text. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, Sofia, Bulgaria. [find](https://scholar.google.com/scholar?q=Mohamed+Amir+Yosef%2C+Sandro+Bauer%2C+Johannes+Hoffart+Marc+Spaniol%2C+and+Gerhard+Weikum%2E+2013%2E+HYENA%2Dlive%3A+Fine%2DGrained+Online+Entity+Type+Classification+from+Natural%2Dlanguage+Text%2E+In+Proceedings+of+the+)
26. Mohamed Amir Yosef, Marc Spaniol, and Gerhard Weikum. 2014. [AIDArabic: A Named-Entity Disambiguation Framework for Arabic Text](https://md.research.elamur.ai/free/en/papers/yosef-2014-aidarabic-named-entity-disambiguation-framework/). In The EMNLP 2014 Workshop on Arabic Natural Language Processing, ANLP 2014, Dohar, Qatar.

*Updated 2 November 2026*