---
title: "A New Representation Model for the Automatic Recognition and"
description: "The authors propose a feature-structure model for Arabic NEs, inspired by HPSG and Bourigault's \"Head and… 94% F-measure. 14 references."
authors: ["Héla Fehri", "Kais Haddar", "Abdelmajid Ben hamadou"]
year: 2011
venue: "Proceedings of the International Conference Recent Advances in Natural Language Processing 2011"
source: "https://aclanthology.org/R11-1076/"
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/fehri-2011-new-representation-model-automatic-recognition/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/fehri-2011-new-representation-model-automatic-recognition/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2011](https://md.research.elamur.ai/free/en/papers/2011/page/2/) / A New Representation Model for the Automatic Recognition and Translation of Arabic Named Entities with NooJ

# A New Representation Model for the Automatic Recognition and Translation of Arabic Named Entities with NooJ

**Authors:** [Héla Fehri](https://md.research.elamur.ai/free/en/authors/hela-fehri/), [Kais Haddar](https://md.research.elamur.ai/free/en/authors/kais-haddar/) and [Abdelmajid Ben hamadou](https://md.research.elamur.ai/free/en/authors/abdelmajid-ben-hamadou/) · **Year:** 2011 · **Venue:** [Proceedings of the International Conference Recent Advances in Natural Language Processing 2011](https://md.research.elamur.ai/free/en/venues/ranlp/) ([RANLP 2011](https://md.research.elamur.ai/free/en/venues/ranlp/2011/)) · **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/R11-1076/) · [PDF](https://aclanthology.org/R11-1076.pdf) · [OpenAlex](https://openalex.org/W763453797)

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

## Summary
Arabic named entities are hard to detect and translate. They carry no capitalisation cue, their length is unpredictable, and they often contain other entities nested inside them. The authors propose a feature-structure model for Arabic NEs, inspired by HPSG and Bourigault's "Head and Expansion" notions. In this model an entity has a type, usually signalled by a trigger word, and a recursive essential part (the head). It can also have an optional extensional ending introduced by a non-entity element such as a preposition. Two principles, saturation and non-saturation, decide whether a structure counts as a well-formed NE. The model guides which NooJ grammars and dictionaries to build, using bilingual Arabic–French lexicons focused on sport-domain place names. Recognition runs as a separate phase before translation. On a sport corpus recognition reaches 94% F-measure, and about 97% of extracted NEs are translated correctly. The work matters because separating recognition from translation lets the same resources be reused across target languages and domains.

## Key points
- **Recognition on sport texts.** The test corpus is 4000 sport texts (94.5 MB) with 180,000 NEs, of which 40,000 are place names. Results are 98% precision, 90% recall and 94% F-measure.
- **Recognition on education texts.** The test corpus is 300 education texts (14.5 MB) containing 3000 university institution names. Results are 98% precision, 70% recall and 82% F-measure; recall falls because dictionaries are incomplete and some transducer paths are missing.
- **New dictionaries.** Each entry has a French translation:
  - Team Names (5785 entries)
  - Sport Names (337)
  - Capital and country Names (610)
  - Personality Names (300)
  - Trigger words (20)
  - Functions Names (100)
  
  First names stay monolingual and are transliterated later.
- **Model features.** The features are ″Tête_EN″, ″Mot_déclencheur″, ″Fin_EN″, ″Type_EN″ and ″Element_EN″, and the hierarchy of types is derived from MUC. When several transducer paths match, the longest one is kept.
- **Translation challenges.** Arabic to French translation must handle:
  - gender mismatches (masculine Arabic "swimming pool" vs. feminine *piscine*);
  - capital-vs-country ambiguity (Tunis/Tunisie);
  - adjective reordering.
  
  Word-to-word output therefore needs readjustment rules afterwards.

## Interesting ideas
- An entity name is modelled as a type plus a recursive head plus an optional tail, where the tail is introduced by a non-entity element such as a preposition; this makes nested names explicit rather than flat spans.
- A saturation test counts a structure as an entity only if its typed head is non-empty; a prepositional fragment like "in Riyadh" is unsaturated but may still contain an entity.
- The formal model itself determines the resources: structured heads become grammars and atomic elementary entities become dictionary entries.
- Recognition is kept separate from translation, and literal per-feature transfer is followed by target-side readjustment rules for gender, word order and sense choice.
- A co-occurring modifier picks between candidate translations, for example "sportive" favours one sense of *madina* over the other.

## For Mova

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

- **I1** (world): Entity mentions like "King Abdelaziz International Stadium in Riyadh" could be stored as nested entities (a stadium headed by a person name and located at a city), so the world model gets the containment and location links for free.
- **I2** (world): Before an entity is created in the world of the text, a similar well-formedness check could reject fragments that lack a typed head while still descending into them for embedded entities.
- **I3** (world): Compiled knowledge could be organised the same way, with atomic names going into the lexicon or knowledge graph and compositional name patterns into rules, which keeps each resource traceable to the model.
- **I4** (back): Generation from the meaning graph could first map each node literally and then apply explainable target-language repair rules, so each fix stays inspectable.
- **I5** (back): When a graph node has several surface realisations, its attached modifiers in the graph could vote on the choice, rather than relying on a global frequency default.

*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

- [University of Sfax](https://md.research.elamur.ai/free/en/universities/university-of-sfax/) — University, Sfax, Tunisia · 17 works · 233 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: Héla Fehri, Kais Haddar and Abdelmajid Ben hamadou. 2011. A New Representation Model for the Automatic Recognition and Translation of Arabic Named Entities with NooJ. Proceedings of the International Conference Recent Advances in Natural Language Processing 2011.

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

```bibtex
@inproceedings{fehri2011new,
  title = {{A New Representation Model for the Automatic Recognition and Translation of Arabic Named Entities with NooJ}},
  author = {Héla Fehri, Kais Haddar and Abdelmajid Ben hamadou},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing 2011},
  year = {2011},
  url = {https://aclanthology.org/R11-1076/}
}
```

- [← previous Semantic Information and Derivation Rules for Robust Dialogue Act Detection in a Spoken Dialogue System](https://md.research.elamur.ai/free/en/papers/liang-2011-semantic-information-derivation-rules-robust/)
- [next → Adaptive Feedback Message Generation for Second Language Learners of Arabic](https://md.research.elamur.ai/free/en/papers/shaalan-2011-adaptive-feedback-message-generation-second/)
- [↑ back to papers of 2011](https://md.research.elamur.ai/free/en/papers/2011/page/2/)

## References

14 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Barreiro, A. 2008. Port4NooJ: an open source, ontology-driven Portuguese linguistic system with applications in machine translation. NooJ’08, Budapest. [find](https://scholar.google.com/scholar?q=Barreiro%2C+A%2E+2008%2E+Port4NooJ%3A+an+open+source%2C+ontology%2Ddriven+Portuguese+linguistic+system+with+applications+in+machine+translation%2E+NooJ%E2%80%9908%2C+Budapest%2E)
2. Borthwick, A., Sterling, J., Agichtein, E. Grishman, R. 1998. NYU: Description of the MENE Named Entity System as used in MUC-7. In Proc. of the Seventh Message Understanding Conference (MUC-7). [find](https://scholar.google.com/scholar?q=Borthwick%2C+A%2E%2C+Sterling%2C+J%2E%2C+Agichtein%2C+E%2E+Grishman%2C+R%2E+1998%2E+NYU%3A+Description+of+the+MENE+Named+Entity+System+as+used+in+MUC%2D7%2E+In+Proc%2E+of+the+Seventh+Message+Understanding+Conference+%28MUC%2D7%29%2E)
3. Bourigault, D. 2002. UPERY : un outil d'analyse distributionnelle étendue pour la construction d’ontologies à partir de corpus. TALN. [find](https://scholar.google.com/scholar?q=Bourigault%2C+D%2E+2002%2E+UPERY+%3A+un+outil+d%27analyse+distributionnelle+%C3%A9tendue+pour+la+construction+d%E2%80%99ontologies+%C3%A0+partir+de+corpus%2E+TALN%2E)
4. Coates-Stephens, S. 1993. The Analysis and Acquisition of Proper Names for the Understanding of Free Text. In Computers and the Humanities, Kluwer Academic Publishers, Vol. 26(5-6), Hingham, MA, p. 441-456. [find](https://scholar.google.com/scholar?q=Coates%2DStephens%2C+S%2E+1993%2E+The+Analysis+and+Acquisition+of+Proper+Names+for+the+Understanding+of+Free+Text%2E+In+Computers+and+the+Humanities%2C+Kluwer+Academic+Publishers%2C+Vol%2E+26%285%2D6%29%2C+Hingham%2C+MA%2C+p%2E+44)
5. Friburger, N. 2002. Reconnaissance automatique des noms propres. PhD thesis, university of François Rabelais. [find](https://scholar.google.com/scholar?q=Friburger%2C+N%2E+2002%2E+Reconnaissance+automatique+des+noms+propres%2E+PhD+thesis%2C+university+of+Fran%C3%A7ois+Rabelais%2E)
6. Grishman, R. 1995. Where's the Syntax? The NYU MUC-6 System. In Acts of MUC-6, Morgan Kaufmann Publishers, San Francisco. [find](https://scholar.google.com/scholar?q=Grishman%2C+R%2E+1995%2E+Where%27s+the+Syntax%3F+The+NYU+MUC%2D6+System%2E+In+Acts+of+MUC%2D6%2C+Morgan+Kaufmann+Publishers%2C+San+Francisco%2E)
7. Hasni, E., Haddar, K., Abdelwahed, A. 2009. Reconnaissance des expressions elliptiques arabes avec NOOJ. In proceedings of the 3rd International Conference on Arabic Language Processing (CITALA’09) sponsored by IEEE Morocco Section, 4-5 May 2009, Rabat, Morocco, pp 83-88. [find](https://scholar.google.com/scholar?q=Hasni%2C+E%2E%2C+Haddar%2C+K%2E%2C+Abdelwahed%2C+A%2E+2009%2E+Reconnaissance+des+expressions+elliptiques+arabes+avec+NOOJ%2E+In+proceedings+of+the+3rd+International+Conference+on+Arabic+Language+Processing+%28CITALA%E2%80%9909%29+sp)
8. Mesfar, S. 2007. Named Entity Recognition for Arabic Using Syntactic grammars. NLDB 2007 Paris, 28-38. [find](https://scholar.google.com/scholar?q=Mesfar%2C+S%2E+2007%2E+Named+Entity+Recognition+for+Arabic+Using+Syntactic+grammars%2E+NLDB+2007+Paris%2C+28%2D38%2E)
9. Mikheev, A., Grover, C. et Moens, M. 1998. Description of the LTG system used for MUC -7. In Proc. of 7th Message Understanding Conference (MUC-7), [http://www.itl.nist.gov/iad/](http://www.itl.nist.gov/iad/) 894.02/ related_projects/muc/. [↗](http://www.itl.nist.gov/iad/)
10. Poibeau, T. 2005. Sur le statut référentiel des entités nommées. Laboratory of data processing of Paris North – CNRS and University Paris 13. [find](https://scholar.google.com/scholar?q=Poibeau%2C+T%2E+2005%2E+Sur+le+statut+r%C3%A9f%C3%A9rentiel+des+entit%C3%A9s+nomm%C3%A9es%2E+Laboratory+of+data+processing+of+Paris+North+%E2%80%93+CNRS+and+University+Paris+13%2E)
11. Pollard, C., Sag., I.A. 1994. Head-Driven Phrase Structure Grammar. Published by the press in the University of Chicago, Edition Golgoldmittu, Chicago, LSLI. [find](https://scholar.google.com/scholar?q=Pollard%2C+C%2E%2C+Sag%2E%2C+I%2EA%2E+1994%2E+Head%2DDriven+Phrase+Structure+Grammar%2E+Published+by+the+press+in+the+University+of+Chicago%2C+Edition+Golgoldmittu%2C+Chicago%2C+LSLI%2E)
12. Shaalan, K., Raza, H. 2009. NERA: Named Entity Recognition for Arabic. Published in Journal of the American Society for Information Science and Technology, Volume 60 Issue 8. [find](https://scholar.google.com/scholar?q=Shaalan%2C+K%2E%2C+Raza%2C+H%2E+2009%2E+NERA%3A+Named+Entity+Recognition+for+Arabic%2E+Published+in+Journal+of+the+American+Society+for+Information+Science+and+Technology%2C+Volume+60+Issue+8%2E)
13. Silberztein, M. 2004. NooJ : an Object-Oriented Approach. In INTEX pour la Linguistique et le Traitement Automatique des Langues. C. Muller, J. Royauté M. Silberztein Eds, book of the MSH Ledoux. Presses University of Franche-Comte, pp. 359-369. [find](https://scholar.google.com/scholar?q=Silberztein%2C+M%2E+2004%2E+NooJ+%3A+an+Object%2DOriented+Approach%2E+In+INTEX+pour+la+Linguistique+et+le+Traitement+Automatique+des+Langues%2E+C%2E+Muller%2C+J%2E+Royaut%C3%A9+M%2E+Silberztein+Eds%2C+book+of+the+MSH+Ledoux%2E+Pres)
14. Wu, M. 2008. La traduction automatique français-chinois pour les groupes nominaux avec NooJ. Budapest. [find](https://scholar.google.com/scholar?q=Wu%2C+M%2E+2008%2E+La+traduction+automatique+fran%C3%A7ais%2Dchinois+pour+les+groupes+nominaux+avec+NooJ%2E+Budapest%2E)

*Updated 2 November 2026*