---
title: "Mapping Interlingua Representations to Feature Structures of"
description: "It shows worked examples and discusses the design problems the authors met along the way. 13 references, cited by 1 paper here."
authors: ["Khaled Shaalan", "Azza Abdel Monem", "Ahmed Rafea", "Hoda Baraka"]
year: 2006
venue: "Proceedings of the International Conference on the Challenge of Arabic for NLP/MT"
source: "https://aclanthology.org/2006.bcs-1.12/"
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-2006-mapping-interlingua-representations-feature-structures/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shaalan-2006-mapping-interlingua-representations-feature-structures/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2006](https://md.research.elamur.ai/free/en/papers/2006/page/2/) / Mapping Interlingua Representations to Feature Structures of Arabic Sentences

# Mapping Interlingua Representations to Feature Structures of Arabic Sentences

**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/), [Ahmed Rafea](https://md.research.elamur.ai/free/en/authors/ahmed-rafea/) and Hoda Baraka · **Year:** 2006 · **Venue:** [Proceedings of the International Conference on the Challenge of Arabic for NLP/MT](https://md.research.elamur.ai/free/en/venues/bcs/) ([International Conference on the Challenge of Arabic for NLP/MT 2006](https://md.research.elamur.ai/free/en/venues/bcs/2006/)) · **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/2006.bcs-1.12/) · [PDF](https://aclanthology.org/2006.bcs-1.12.pdf) · [OpenAlex](https://openalex.org/W2715317759)

**Citations:** 4 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/shaalan-2006-mapping-interlingua-representations-feature-structures/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
In interlingua machine translation, the source sentence is first reduced to a meaning representation, and the target sentence is then generated from it. When that interlingua carries no syntax, the generator must work out the target sentence's structure on its own. The authors address this gap for Arabic within NESPOLE!, a multilingual speech-to-speech MT project for travel and tourism dialogue. Its interlingua, the Interchange Format (IF), encodes speaker intention as a speech act plus concepts and arguments.

They built a rule-based mapper in SICStus Prolog that converts an IF into an Arabic feature structure (FS). The FS is a list of feature-value pairs whose order mirrors the target sentence. The mapper relies on four resources: a domain ontology, a lexicon linking IF elements to Arabic words, one rule set that handles word-level mapping, and another that handles structure. It is demonstrated on IFs produced by CMU's English analyzer.

The paper reports no quantitative evaluation. It shows worked examples and discusses the design problems the authors met along the way. The work matters because Arabic generation had received far less research attention than Arabic analysis.

## Key points
- The mapper works in three stages:
  - preprocessing against the ontology: turning the IF into a Prolog term, attaching arguments to concepts, and checking that the IF is legal;
  - lexical mapping;
  - structure mapping.
- The speech act fixes one of four sentence modes: statement, command, interrogative, or fragment.
- Words are grouped into five constituent types: coordination, subject, verb, interrogative and complement. These are then ordered into the FS by rules in a transformation-grammar style.
- The mapping lexicon has two kinds of entries, general and specific. Both pair an IF element with an Arabic lexeme and its POS.
- Some constituents are implicit and are filled in by rule:
  - the particle هل is inserted for questions that lack an interrogative marker;
  - a "to be" verb is inserted when only a tense argument (e-time) is present;
  - implicit values such as "age" are supplied.
- The IF has no case marking, and Arabic word order is flexible, so the mapper falls back on a fixed set of default NP/verb order patterns with assigned cases. Morphological and surface generation are left for future work.

## Interesting ideas
- Validate the meaning representation against a formal ontology of legal acts, arguments and values before any generation, so malformed input is rejected early rather than producing broken output.
- Derive sentence mode (statement, command, question, fragment) directly from the speech act, then let the mode select which structural rule applies.
- Separate an intermediate syntactic feature structure (ordered constituents with features) from the later morphology and surface-realization step. This keeps structural decisions inspectable on their own.
- Use explicit repair rules that insert constituents the meaning leaves implicit, such as a default copula when only tense is known or a question particle when the question is unmarked.
- When the representation lacks a cue (here, case), pick a small documented set of default orderings instead of guessing freely.

## For Mova

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

- **I1** (back): Check meaning graphs against the frame/ontology schema before generating text, and report the failed constraint as an explainable error.
- **I2** (back): Use the speech-act label from prag to choose the clause template when turning a frame back into an English sentence.
- **I3** (back): Have the text → graph → text compressor emit an ordered constituent structure before inflection, so each stage can be checked and debugged separately.
- **I4** (back): Add named, logged rules that supply copulas, auxiliaries or dummy subjects when a frame lacks a verb but carries tense or mood.
- **I5** (back): Define default argument-order patterns per VerbNet class for generation, and record which default fired so the choice remains explainable.

*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

- [British University in Dubai](https://md.research.elamur.ai/free/en/universities/british-university-in-dubai/) — University, Dubai, United Arab Emirates · 10 works · 587 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): [🔁 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, Ahmed Rafea and Hoda Baraka. 2006. Mapping Interlingua Representations to Feature Structures of Arabic Sentences. Proceedings of the International Conference on the Challenge of Arabic for NLP/MT.

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

```bibtex
@inproceedings{shaalan2006mapping,
  title = {{Mapping Interlingua Representations to Feature Structures of Arabic Sentences}},
  author = {Khaled Shaalan, Azza Abdel Monem, Ahmed Rafea and Hoda Baraka},
  booktitle = {Proceedings of the International Conference on the Challenge of Arabic for NLP/MT},
  year = {2006},
  url = {https://aclanthology.org/2006.bcs-1.12/}
}
```

- [← previous A Factored Functional Dependency Transformation of the English Penn Treebank for Probabilistic Surface Generation](https://md.research.elamur.ai/free/en/papers/geary-2006-factored-functional-dependency-transformation-english/)
- [next → A Hebrew Tree Bank Based on Cantillation Marks](https://md.research.elamur.ai/free/en/papers/wu-2006-hebrew-tree-bank-based-cantillation/)
- [↑ back to papers of 2006](https://md.research.elamur.ai/free/en/papers/2006/page/2/)

## References

13 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abul seoud, R. (2005). Generating Interlingua from Arabic Parsing Tree, M. Sc., Faculty of Engineering, Cairo University, Egypt. [find](https://scholar.google.com/scholar?q=Abul+seoud%2C+R%2E+%282005%29%2E+Generating+Interlingua+from+Arabic+Parsing+Tree%2C+M%2E+Sc%2E%2C+Faculty+of+Engineering%2C+Cairo+University%2C+Egypt%2E)
2. Cavalli-Sforza, V., Soudi, A., and Mitamura, T. (2000). [Arabic Morphology Generation Using a Concatenative Strategy](https://md.research.elamur.ai/free/en/papers/sforza-2000-arabic-morphology-generation-concatenative-strategy/), In the Proceedings of the 1st Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL 2000), Seattle, PP. 86-93.
3. Habash, N. (2004).Large scale lexeme based Arabic morphological generation. In Proceedings of Traitement Automatique du Langage Naturel (TALN-04). Fez, Morocco. [find](https://scholar.google.com/scholar?q=Habash%2C+N%2E+%282004%29%2ELarge+scale+lexeme+based+Arabic+morphological+generation%2E+In+Proceedings+of+Traitement+Automatique+du+Langage+Naturel+%28TALN%2D04%29%2E+Fez%2C+Morocco%2E)
4. Leavitt, J. (1994). MORPHE: A Morphological Rule Compiler. Technical Report, CMU-CMT-94-MEMO. [find](https://scholar.google.com/scholar?q=Leavitt%2C+J%2E+%281994%29%2E+MORPHE%3A+A+Morphological+Rule+Compiler%2E+Technical+Report%2C+CMU%2DCMT%2D94%2DMEMO%2E)
5. Levin, L., Lavie, A., Woszczyna, M., Gates, D., Gavalda, M., Koll, D., and Waibel, A. (2000). The Janus III Translation System: Speech-to-Speech Translation in Multiple Domains, Machine Translation, 15(1-2), PP. 3-25. [find](https://scholar.google.com/scholar?q=Levin%2C+L%2E%2C+Lavie%2C+A%2E%2C+Woszczyna%2C+M%2E%2C+Gates%2C+D%2E%2C+Gavalda%2C+M%2E%2C+Koll%2C+D%2E%2C+and+Waibel%2C+A%2E+%282000%29%2E+The+Janus+III+Translation+System%3A+Speech%2Dto%2DSpeech+Translation+in+Multiple+Domains%2C+Machine+Translation%2C+1)
6. Levin, L., Gates, D., Wallace, D., Peterson, K., Pianta, E., and Mana, N. (2003). The NESPOLE! Interchange Format, Project Deliverable D13. [find](https://scholar.google.com/scholar?q=Levin%2C+L%2E%2C+Gates%2C+D%2E%2C+Wallace%2C+D%2E%2C+Peterson%2C+K%2E%2C+Pianta%2C+E%2E%2C+and+Mana%2C+N%2E+%282003%29%2E+The+NESPOLE%21+Interchange+Format%2C+Project+Deliverable+D13%2E)
7. Metze, F., McDonough, J., Soltau, H., Lavie, A., Levin, L., Langley, C., Schultz, T., Waibel, A., Cattoni,R., Lazzari, G., Mana, N., Pianesi, F., and Pianta, E.. (2002). Enhancing the Usability and Performance of NESPOLE! - a Real-World Speech-to-Speech Translation System. In Proceedings of HLT-2002 Human Language Technology Conference, San Diego, CA. [find](https://scholar.google.com/scholar?q=Metze%2C+F%2E%2C+McDonough%2C+J%2E%2C+Soltau%2C+H%2E%2C+Lavie%2C+A%2E%2C+Levin%2C+L%2E%2C+Langley%2C+C%2E%2C+Schultz%2C+T%2E%2C+Waibel%2C+A%2E%2C+Cattoni%2CR%2E%2C+Lazzari%2C+G%2E%2C+Mana%2C+N%2E%2C+Pianesi%2C+F%2E%2C+and+Pianta%2C+E%2E%2E+%282002%29%2E+Enhancing+the+Usability+and+Pe)
8. Mitamura T., Nyberg, E. (1992). Hierarchical Lexical Structure and Interpretive Mapping in Machine Translation, In the Proceedings of COLING-92. [find](https://scholar.google.com/scholar?q=Mitamura+T%2E%2C+Nyberg%2C+E%2E+%281992%29%2E+Hierarchical+Lexical+Structure+and+Interpretive+Mapping+in+Machine+Translation%2C+In+the+Proceedings+of+COLING%2D92%2E)
9. Nwesri, A., Tahaghoghi, S., and Scholer. F. (2005). String Processing and Information Retrieval: 12th International Conference, SPIRE 2005, Buenos Aires, Argentina, LNCS, Springer Berlin / Heidelberg, PP. 206 – 217. [find](https://scholar.google.com/scholar?q=Nwesri%2C+A%2E%2C+Tahaghoghi%2C+S%2E%2C+and+Scholer%2E+F%2E+%282005%29%2E+String+Processing+and+Information+Retrieval%3A+12th+International+Conference%2C+SPIRE+2005%2C+Buenos+Aires%2C+Argentina%2C+LNCS%2C+Springer+Berlin+%2F+Heidelberg%2C)
10. Shaalan, K., Abdel Monem, A., and Rafea, A. (2006). Arabic Morphological Generation from Interlingua, 4th International Conference on Intelligent Information Processing (ICIIP), 20-23 September, Adelaide Australia. [find](https://scholar.google.com/scholar?q=Shaalan%2C+K%2E%2C+Abdel+Monem%2C+A%2E%2C+and+Rafea%2C+A%2E+%282006%29%2E+Arabic+Morphological+Generation+from+Interlingua%2C+4th+International+Conference+on+Intelligent+Information+Processing+%28ICIIP%29%2C+20%2D23+September%2C+Adela)
11. Soudi,, A., Cavalli-Sforza, V., and Jamari, A. (2002). A Prototype English-to-Arabic Interlingua-based MT System, In the Proceedings of the Workshop on Arabic Language Re-sources and Evaluation - Status and Prospects, The 3rd International Conference on Language Resources and Evaluation (LREC 2002), Las Palmas de Gran Canaria, Spain. [find](https://scholar.google.com/scholar?q=Soudi%2C%2C+A%2E%2C+Cavalli%2DSforza%2C+V%2E%2C+and+Jamari%2C+A%2E+%282002%29%2E+A+Prototype+English%2Dto%2DArabic+Interlingua%2Dbased+MT+System%2C+In+the+Proceedings+of+the+Workshop+on+Arabic+Language+Re%2Dsources+and+Evaluation+%2D+Stat)
12. Sughaiyer I. and Al-Kharashi,I. (2004). Arabic Morphological Analysis Techniques: A Comprehensive Survey. Journal of The American Society for Information Science and Technology, 55(3):189-213. [find](https://scholar.google.com/scholar?q=Sughaiyer+I%2E+and+Al%2DKharashi%2CI%2E+%282004%29%2E+Arabic+Morphological+Analysis+Techniques%3A+A+Comprehensive+Survey%2E+Journal+of+The+American+Society+for+Information+Science+and+Technology%2C+55%283%29%3A189%2D213%2E)
13. Tomita, M., Nyberg, E. (1988). Generation Kit and Transformation Kit, Version 3.2, User's, Manual, Technical Report, Carnegie Mellon-Center for Machine Translation. [find](https://scholar.google.com/scholar?q=Tomita%2C+M%2E%2C+Nyberg%2C+E%2E+%281988%29%2E+Generation+Kit+and+Transformation+Kit%2C+Version+3%2E2%2C+User%27s%2C+Manual%2C+Technical+Report%2C+Carnegie+Mellon%2DCenter+for+Machine+Translation%2E)

*Updated 30 October 2026*