---
title: "Syntactic Generation of Arabic in Interlingua-based Machine"
description: "The paper tackles generating Arabic text from a language-neutral meaning representation (Interlingua) within NESPOLE!, a… 15 references."
authors: ["Khaled Shaalan", "Azza Abdel Monem", "Ahmed Rafea"]
year: 2009
venue: "Proceedings of the Third Workshop on Computational Approaches to Arabic-Script-based Languages (CAASL3)"
source: "https://aclanthology.org/2009.mtsummit-caasl.9/"
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/shaalan-2009-syntactic-generation-arabic-interlingua-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shaalan-2009-syntactic-generation-arabic-interlingua-based/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2009](https://md.research.elamur.ai/free/en/papers/2009/page/2/) / Syntactic Generation of Arabic in Interlingua-based Machine Translation Framework

# Syntactic Generation of Arabic in Interlingua-based Machine Translation Framework

**Authors:** [Khaled Shaalan](https://md.research.elamur.ai/free/en/authors/khaled-shaalan/), [Azza Abdel Monem](https://md.research.elamur.ai/free/en/authors/azza-abdel-monem/) and [Ahmed Rafea](https://md.research.elamur.ai/free/en/authors/ahmed-rafea/) · **Year:** 2009 · **Venue:** [Proceedings of the Third Workshop on Computational Approaches to Arabic-Script-based Languages (CAASL3)](https://md.research.elamur.ai/free/en/venues/mtsummit/) ([Machine Translation Summit (MT Summit) 2009](https://md.research.elamur.ai/free/en/venues/mtsummit/2009/)) · **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/2009.mtsummit-caasl.9/) · [PDF](https://aclanthology.org/2009.mtsummit-caasl.9.pdf) · [OpenAlex](https://openalex.org/W3214081679)

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

## Summary
The paper tackles generating Arabic text from a language-neutral meaning representation (Interlingua) within NESPOLE!, a multilingual speech-to-speech translation project for e-commerce and travel dialogues. Before this work, Arabic generation from Interlingua had only been attempted with templates. Tools borrowed from Latin-script languages had handled only limited verb and noun forms and could not assign grammatical roles. The authors built a rule-based generator in two layers.

- **Morphology.** A morphological generator inflects stems, which are stored as feature structures in an Arabic lexicon.
- **Syntax.** A syntactic generator assembles the sentence. It enforces agreement between constituents and adds prepositions that the Interlingua leaves implicit.

They tested the system on 300 English semantic dialogue units (SDUs) from the NESPOLE! Travel & Tourism data, scoring the Arabic output with BLEU. The score was 0.65 against one human reference and 0.82 against two. The work matters as an early demonstration that a morphologically rich, relatively free-order language can be produced by explicit linguistic rules from a shared meaning layer, with no fixed templates.

## Key points
- **Setting:** an Arabic generator for the Interlingua of the NESPOLE! (NEgotiating through SPOken Language in E-commerce) speech-to-speech MT project. The authors describe it as the first rule-based syntactic generation of Arabic in an Interlingua framework.
- **Lexicon representation:** words are feature structures.
  - Nouns carry stem, gender, number, definiteness, case and irregular plural.
  - Verbs carry pattern, subject person/number/gender, tense, aspect, voice, transitivity and an irregular past form.
  - Particles carry stem, category and sub-category.
- **Morphological rules:** each rule applies exactly one feature:value change to a stem, using a condition–action pair. Multi-feature forms, such as a definite plural noun, are built by applying rules one after another.
- **Agreement handled by the syntactic layer:**
  - Verb–subject agreement. In VSO order the verb agrees only in gender; in SVO it agrees in gender and number.
  - Demonstrative–noun agreement in gender and definiteness.
  - Number–counted noun agreement. For numbers 3–9, the numeral takes the gender opposite to the singular form of the counted noun.
- **Evaluation:** NIST MT kit version 09, with references from a professional translator. BLEU was 0.65 with one reference and 0.82 with two; budget allowed only two references. Planned future work is automatic diacritization for Arabic TTS.

## Interesting ideas
- Inflection is broken into atomic rules, each changing a single feature under explicit conditions, so a complex form becomes a traceable sequence of small edits.
- Agreement is treated as a separate generation phase that runs after constituents are chosen, so features such as gender and definiteness are copied between linked words according to word order.
- Function words that the meaning layer omits, like prepositions marking "day of month" or a verb's complement, are restored by heuristic rules tied to particular verbs, nouns or argument types. These insertions can also change the form of the words that follow.
- The same output is scored against one reference and then two, which shows how strongly a single-reference metric understates quality for free-order languages.

## For Mova

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

- **I1** (tokens): The English morphology in crate en could log each lemma→form step as a separate rule application, which makes every inflection explainable and easy to debug.
- **I2** (back): When rendering the meaning graph to text, a post-pass could enforce subject–verb and determiner–noun agreement from the UD relations, instead of trusting each word to be chosen correctly in isolation.
- **I3** (back): The text → graph → text compressor could restore prepositions from VerbNet frame roles and then re-check the dependent words, since the inserted word may change what follows.
- **I4** (learn): Mova's generation and translation evaluations could report scores at several reference counts, so that low scores are not wrongly blamed on the generator when they reflect legitimate paraphrase variety.

*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 (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): [🔁 Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) · 1,087 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Khaled Shaalan, Azza Abdel Monem and Ahmed Rafea. 2009. Syntactic Generation of Arabic in Interlingua-based Machine Translation Framework. Proceedings of the Third Workshop on Computational Approaches to Arabic-Script-based Languages (CAASL3).

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

```bibtex
@inproceedings{shaalan2009syntactic,
  title = {{Syntactic Generation of Arabic in Interlingua-based Machine Translation Framework}},
  author = {Khaled Shaalan, Azza Abdel Monem and Ahmed Rafea},
  booktitle = {Proceedings of the Third Workshop on Computational Approaches to Arabic-Script-based Languages (CAASL3)},
  year = {2009},
  url = {https://aclanthology.org/2009.mtsummit-caasl.9/}
}
```

- [← previous Sobre as noções ‘nativo’/não nativo’: uma dicotomia perigosa para o inglês global? On the notions “native”/”nonnative”: a dangerous dichotomy for World Englishes?](https://md.research.elamur.ai/free/en/papers/schmitz-2009-sobre-nocoes-nativo-nao-nativo/)
- [next → Theorizing in the Absence of a Theory:The Case of the Aramaic Targums to the Pentateuch](https://md.research.elamur.ai/free/en/papers/lasair-2009-theorizing-absence-theory-case-aramaic/)
- [↑ back to papers of 2009](https://md.research.elamur.ai/free/en/papers/2009/page/2/)

## References

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

1. Yasuhiro Akiba, Marcello Federico, Noriko Kando, Hiromi Nakaiwa, Michael Paul and Jun’ichi Tsujii. 2004. Overview of the IWSLT04 evaluation campaign, In Proceedings of the International workshop on spoken language translation, Kyoto, Japan, pp. 1-12, 30 September–1 October. [find](https://scholar.google.com/scholar?q=Yasuhiro+Akiba%2C+Marcello+Federico%2C+Noriko+Kando%2C+Hiromi+Nakaiwa%2C+Michael+Paul+and+Jun%E2%80%99ichi+Tsujii%2E+2004%2E+Overview+of+the+IWSLT04+evaluation+campaign%2C+In+Proceedings+of+the+International+workshop+on+sp)
2. Mohammed Attia. 2008. Handling Arabic Morphological and Syntactic Ambiguities within the LFG Framework with a View to Machine Translation. Dissertation, University of Manchester, UK. [find](https://scholar.google.com/scholar?q=Mohammed+Attia%2E+2008%2E+Handling+Arabic+Morphological+and+Syntactic+Ambiguities+within+the+LFG+Framework+with+a+View+to+Machine+Translation%2E+Dissertation%2C+University+of+Manchester%2C+UK%2E)
3. Violetta Cavalli-Sforza, Abdelhadi Soudi, and Teruko Mitamura. 2000. [Arabic morphology generation using a concatenative strategy](https://md.research.elamur.ai/free/en/papers/sforza-2000-arabic-morphology-generation-concatenative-strategy/). In Proceedings of the North American Association For Computational Linguistics (NAACL), Seattle, USA, pp. 86-93, 29 April- 3 May.
4. Robert Geist. 1971. An Introduction to Transformation Grammar. Macmillan, New York, USA. [find](https://scholar.google.com/scholar?q=Robert+Geist%2E+1971%2E+An+Introduction+to+Transformation+Grammar%2E+Macmillan%2C+New+York%2C+USA%2E)
5. LDC. 2002. Linguistic data annotation specification: Assessment of fluency and adequacy in Chinese-English translations, Revision 1.0, Linguistic Data Consortium, University of Pennsylvania, USA. [find](https://scholar.google.com/scholar?q=LDC%2E+2002%2E+Linguistic+data+annotation+specification%3A+Assessment+of+fluency+and+adequacy+in+Chinese%2DEnglish+translations%2C+Revision+1%2E0%2C+Linguistic+Data+Consortium%2C+University+of+Pennsylvania%2C+USA%2E)
6. John Mace. 1998. Arabic Grammar: A Reference Guide. [find](https://scholar.google.com/scholar?q=John+Mace%2E+1998%2E+Arabic+Grammar%3A+A+Reference+Guide%2E)
7. Edinburgh University Press, Edinburgh, UK Karin Ryding. 2005. Reference Grammar of Modern Standard Arabic, Cambridge University Press, New York, USA. [find](https://scholar.google.com/scholar?q=Edinburgh+University+Press%2C+Edinburgh%2C+UK+Karin+Ryding%2E+2005%2E+Reference+Grammar+of+Modern+Standard+Arabic%2C+Cambridge+University+Press%2C+New+York%2C+USA%2E)
8. Ahmed Rafea and Khaled Shaalan. 1993. Lexical Analysis of Inflected Arabic words using Exhaustive Search of an Augmented Transition Network, Software Practice and Experience, John Wiley & sons Ltd., UK, 23(6):567-588. [find](https://scholar.google.com/scholar?q=Ahmed+Rafea+and+Khaled+Shaalan%2E+1993%2E+Lexical+Analysis+of+Inflected+Arabic+words+using+Exhaustive+Search+of+an+Augmented+Transition+Network%2C+Software+Practice+and+Experience%2C+John+Wiley+%26+sons+Ltd%2E%2C+U)
9. Khaled Shaalan. 2005b. Arabic GramCheck: A grammar checker for Arabic. Software Practice and Experience, John Wiley & sons Ltd., UK, 35(7):643-665. [↗](https://doi.org/10.1002/spe.653)
10. Khaled Shaalan, Azza Abdel Monem, and Ahmed Rafea. 2006a. Arabic morphological generation from Interlingua: A rule-based approach. In: Shi Z, Shimohara K, Feng D (eds) Intelligent Information Processing III, International Federation for Information Processing (IFIP), vol 228. Springer, Boston, pp441-451. [find](https://scholar.google.com/scholar?q=Khaled+Shaalan%2C+Azza+Abdel+Monem%2C+and+Ahmed+Rafea%2E+2006a%2E+Arabic+morphological+generation+from+Interlingua%3A+A+rule%2Dbased+approach%2E+In%3A+Shi+Z%2C+Shimohara+K%2C+Feng+D+%28eds%29+Intelligent+Information+Processi)
11. Khaled Shaalan, Azza Abdel Monem, Ahmed Rafea, and Hoda Baraka. 2006b. [Mapping Interlingua representations to feature structures of Arabic sentences](https://md.research.elamur.ai/free/en/papers/shaalan-2006-mapping-interlingua-representations-feature-structures/), The challenge of Arabic for NLP/MT international conference, the British Computer Society (BCS), London, UK pp. 149-159, 23 October.
12. Khaled Shaalan, Azza Abdel Monem, Ahmed Rafea, and Hoda Baraka. 2007. Generating Arabic text from Interlingua. In Proceedings of the 2nd workshop on computational approaches to Arabic script-based languages (CAASL-2), Linguistic Institute, Stanford, California, USA, pp. 137-144, 21-22 July. [find](https://scholar.google.com/scholar?q=Khaled+Shaalan%2C+Azza+Abdel+Monem%2C+Ahmed+Rafea%2C+and+Hoda+Baraka%2E+2007%2E+Generating+Arabic+text+from+Interlingua%2E+In+Proceedings+of+the+2nd+workshop+on+computational+approaches+to+Arabic+script%2Dbased+lan)
13. Abdelhadi Soudi, Violetta Cavalli-Sforza, and Abderrahim Jamari. 2002. A prototype English-to-Arabic Interlingua-based MT system In Proceedings of the workshop on Arabic language resources and evaluation: Status and prospects, 3rd international conference on language resources and evaluation (LREC 2002), Las Palmas de Gran Canaria, Spain, pp. 18-25, 1 June. [find](https://scholar.google.com/scholar?q=Abdelhadi+Soudi%2C+Violetta+Cavalli%2DSforza%2C+and+Abderrahim+Jamari%2E+2002%2E+A+prototype+English%2Dto%2DArabic+Interlingua%2Dbased+MT+system+In+Proceedings+of+the+workshop+on+Arabic+language+resources+and+evaluat)
14. Alex Waibel, Ahmed Badran, Alan Black, Robert Frederking, Donna Gates, Alon Lavie, Lori Levin, Kevin Lenzo, Laura Mayfield Tomokiyo, Jürgen Reichert, Tanja Schultz, Dorcas Wallace, Monika Woszczyna, Jing Zhang. 2003a. Speechalator: Two-way speech-to-speech translation on a consumer PDA. In Proceedings of EUROSPEECH 2003, Geneva, Switzerland, pp. 369-372. [↗](https://doi.org/10.5445/ir/1000183174)
15. Alex Waibel, Ahmed Badran, Alan W Black, Robert Frederking, Donna Gates, Alon Lavie, Lori Levin, Kevin Lenzo, Laura Mayfield Tomokiyo, Juergen Reichert, Tanja Schultz, Dorcas Wallace, Monika Woszczyna, Jing Zhang. 2003b. Speechalator: Two-way speech-to-speech translation in your hand. In Proceedings of the Joint Human Language Technology Conference and the Annual Meeting of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL), Edmonton, Canada, pp. 29-30. [↗](https://doi.org/10.5445/ir/1000008543)

*Updated 1 November 2026*