---
title: "A Semantic Analyzer for the Comprehension of the Spontaneous"
description: "The paper targets semantic decoding in a spoken-language understanding system for Arabic, developed within the \"Oréodule\"… 26 references."
authors: ["Mourad Mars", "Mounir Zrigui", "Mohamed Belgacem", "Anis Zouaghi"]
year: 2008
venue: "arXiv:1610.02493 · Journal: Research in Computing Science Vol34, 2008, pp. 129-140, ISSN: 1870-4069"
source: "https://arxiv.org/abs/1610.02493"
doi: "10.48550/arxiv.1610.02493"
arxiv: "1610.02493"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/mars-2016-semantic-analyzer-comprehension-spontaneous-arabic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mars-2016-semantic-analyzer-comprehension-spontaneous-arabic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2008](https://md.research.elamur.ai/free/en/papers/2008/page/2/) / A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech

# A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech

**Authors:** [Mourad Mars](https://md.research.elamur.ai/free/en/authors/mourad-mars/), [Mounir Zrigui](https://md.research.elamur.ai/free/en/authors/mounir-zrigui/), [Mohamed Belgacem](https://md.research.elamur.ai/free/en/authors/mohamed-belgacem/) and [Anis Zouaghi](https://md.research.elamur.ai/free/en/authors/anis-zouaghi/) · **Year:** 2008 · **Venue:** arXiv:1610.02493 · Journal: Research in Computing Science Vol34, 2008, pp. 129-140, ISSN: 1870-4069 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1610.02493) · [PDF](https://arxiv.org/pdf/1610.02493) · [DOI 10.48550/arxiv.1610.02493](https://doi.org/10.48550/arxiv.1610.02493) · [arXiv 1610.02493](https://arxiv.org/abs/1610.02493) · [OpenAlex](https://openalex.org/W2531584208)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The paper targets semantic decoding in a spoken-language understanding system for Arabic, developed within the "Oréodule" project on Arabic speech recognition, translation and synthesis. Each meaningful word of a recognized utterance must receive a semantic feature group (FSe). The authors observe that standard models, which condition on a fixed window of immediately preceding words, perform poorly on spontaneous Modern Standard Arabic.

Their decoder works differently. It first drops non-content words through a lexical filter. It then picks, for each target word, the earlier words with the strongest statistical affinity, measured by an average mutual information score. A probabilistic model combines the semantic labels of those words with lexical cues and with the illocutionary type of the utterance (request, refusal, etc.).

The lexicon of features was built with a semi-automatic, human-in-the-loop tool. On a railway-information task, the error rate falls from 48.6–57% for fixed-history baselines to about 20%. This suggests that choosing context by relevance, rather than by position, matters for loosely ordered spontaneous speech.

## Key points
- Each word carries an FSe triple {field, semantic class, micro-semantic feature} plus a syntactic group Fsy {gender, number, nature}. Synonyms, and words with the same semantic role, share one FSe.
- The structure of sense representation (SRS) is built through man/machine cooperation. A human assigns FSe and Fsy, while the system enforces about ten integrity constraints to keep the SRS unambiguous.
- Several unsupervised steps support the decoder:
  - A modified TF×IDF weighting extracts "reference words" that signal the request type.
  - k-means groups words into semantic classes.
  - Average mutual information (IMm), which also accounts for word absence, ranks candidate context words. Ties go to the nearest word.
- The training corpus has 10,000 railway-information utterances labelled with 37 FSe. The test set has 100 timing-request utterances containing 500 expert-assigned FSe.
- Error rates by setup:

  | Setup | Error rate |
  |---|---|
  | Previous word's meaning | 57% |
  | Two previous words' meanings | 48.6% |
  | Adding utterance type and lexical data | 37% |
  | Using only the pertinent FSe | ~20% |

  The remaining errors come mostly from syntactically complex utterances.

## Interesting ideas
- Selecting conditioning context by measured association instead of a fixed n-word window lets distant but relevant words drive disambiguation.
- The speech-act type of the whole utterance (request, refusal, booking vs. timing query) serves as a prior for word-level meaning.
- The mutual information variant counts co-absence as well as co-occurrence, so a word's absence becomes evidence too.
- In the lexicon tool, the human assigns features while the machine checks integrity constraints, for example that distinct words may share a feature set only if they are synonyms.
- Breaking the error analysis down by utterance complexity revealed that the remaining failures concentrate in syntactically hard inputs.

## For Mova

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

- **I1** (frames): when assigning VerbNet roles or frame slots, rank candidate tree neighbours by learned affinity, and record which ones were used so the choice stays explainable.
- **I2** (frames): feed the detected speech act from prag back into word-sense and frame selection, so that an utterance-level decision can narrow lexical readings.
- **I3** (learn): use this richer association score when inducing repair rules or verb-class cues from silver data, so that negative evidence is not thrown away.
- **I4** (world): apply similar automatic consistency checks when compiling the WordNet/FrameNet/Wikidata ontology or verb classes, so that conflicting entries are flagged for review.
- **I5** (answer): report test accuracy grouped by a syntactic complexity measure, to decide when a fallback reading strategy is needed.

*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/) · 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: Mourad Mars, Mounir Zrigui, Mohamed Belgacem and Anis Zouaghi. 2008. A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech. arXiv:1610.02493 · Journal: Research in Computing Science Vol34, 2008, pp. 129-140, ISSN: 1870-4069.

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

```bibtex
@misc{mars2008semantic,
  title = {{A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech}},
  author = {Mourad Mars, Mounir Zrigui, Mohamed Belgacem and Anis Zouaghi},
  year = {2008},
  doi = {10.48550/arxiv.1610.02493},
  eprint = {1610.02493},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1610.02493}
}
```

- [← previous Scalar Implicatures: Pragmatic Inferences or Grammar?](https://md.research.elamur.ai/free/en/papers/lee-2008-scalar-implicatures-pragmatic-inferences-or/)
- [next → Compréhension automatique de la parole arabe spontanée –- Une modélisation numérique Automatic Understanding of Spontaneous Arabic Speech –- A Numerical Model](https://md.research.elamur.ai/free/en/papers/zouaghi-2008-comprehension-automatique-de-la-parole/)
- [↑ back to papers of 2008](https://md.research.elamur.ai/free/en/papers/2008/page/2/)

## References

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

1. Cattoni, R., Federico, M., Lavie, A.: Robust analysis of spoken input combining statistical and knowledge-based information sources. ASRU, Trento (2001) [find](https://scholar.google.com/scholar?q=Cattoni%2C+R%2E%2C+Federico%2C+M%2E%2C+Lavie%2C+A%2E%3A+Robust+analysis+of+spoken+input+combining+statistical+and+knowledge%2Dbased+information+sources%2E+ASRU%2C+Trento+%282001%29)
2. Lefèvre, F.: Estimation de probabilité non paramétrique pour la reconnaissance markovienne de la parole. Thèse de l'Université Pierre et Marie Curie (2000) [find](https://scholar.google.com/scholar?q=Lef%C3%A8vre%2C+F%2E%3A+Estimation+de+probabilit%C3%A9+non+param%C3%A9trique+pour+la+reconnaissance+markovienne+de+la+parole%2E+Th%C3%A8se+de+l%27Universit%C3%A9+Pierre+et+Marie+Curie+%282000%29)
3. Minker, W.: Compréhension automatique de la parole spontanée. L!Harmattan, Paris (1999) [find](https://scholar.google.com/scholar?q=Minker%2C+W%2E%3A+Compr%C3%A9hension+automatique+de+la+parole+spontan%C3%A9e%2E+L%21Harmattan%2C+Paris+%281999%29)
4. Zouaghi, A., Zrigui, M., Ben Ahmed, M.: Une structure sémantique pour l!interprétation des énoncés. JEP-TALN, Fès (2004) [find](https://scholar.google.com/scholar?q=Zouaghi%2C+A%2E%2C+Zrigui%2C+M%2E%2C+Ben+Ahmed%2C+M%2E%3A+Une+structure+s%C3%A9mantique+pour+l%21interpr%C3%A9tation+des+%C3%A9nonc%C3%A9s%2E+JEP%2DTALN%2C+F%C3%A8s+%282004%29)
5. Zouaghi, A., Zrigui, M., Ben Ahmed, M.: Un étiqueteur sémantique des énoncés en langue arabe. RECITAL, Dourdan (2005) [find](https://scholar.google.com/scholar?q=Zouaghi%2C+A%2E%2C+Zrigui%2C+M%2E%2C+Ben+Ahmed%2C+M%2E%3A+Un+%C3%A9tiqueteur+s%C3%A9mantique+des+%C3%A9nonc%C3%A9s+en+langue+arabe%2E+RECITAL%2C+Dourdan+%282005%29)
6. Bousquet-Vernhettes, C.: Compréhension robuste de la parole spontanée dans le dialogue oral homme-machine " Décodage conceptuel stochastique. Thèse de l!université de Toulouse III (2002) [find](https://scholar.google.com/scholar?q=Bousquet%2DVernhettes%2C+C%2E%3A+Compr%C3%A9hension+robuste+de+la+parole+spontan%C3%A9e+dans+le+dialogue+oral+homme%2Dmachine+%22+D%C3%A9codage+conceptuel+stochastique%2E+Th%C3%A8se+de+l%21universit%C3%A9+de+Toulouse+III+%282002%29)
7. Chaabene, N., Belguith, L.: L!étiquetage morpho-syntaxique: comment lever l!ambiguïté dans les textes arabes non voyellés ?. Journées scientifiques des jeunes chercheurs en génie électrique et informatique, Mahdia, Tunisie (2003) [find](https://scholar.google.com/scholar?q=Chaabene%2C+N%2E%2C+Belguith%2C+L%2E%3A+L%21%C3%A9tiquetage+morpho%2Dsyntaxique%3A+comment+lever+l%21ambigu%C3%AFt%C3%A9+dans+les+textes+arabes+non+voyell%C3%A9s+%3F%2E+Journ%C3%A9es+scientifiques+des+jeunes+chercheurs+en+g%C3%A9nie+%C3%A9lectrique+et+informa)
8. Macherey, K., Och, F.J., Ney, H.: Natural Language Understanding Using Statistical Machine Translation. European conference on speech communication and technology, Aalborg (2001) 2205-2208 Mars M., Zrigui M., Belgacem M. and Zouaghi A. [find](https://scholar.google.com/scholar?q=Macherey%2C+K%2E%2C+Och%2C+F%2EJ%2E%2C+Ney%2C+H%2E%3A+Natural+Language+Understanding+Using+Statistical+Machine+Translation%2E+European+conference+on+speech+communication+and+technology%2C+Aalborg+%282001%29+2205%2D2208+Mars+M%2E%2C+Zr)
9. Jain, A.N., Waibel, A., Touretzky, D.S.: Parsec: a structured connexionist parsing system for spoken language. International Conference on Acoustics, Speech and Signal Processing, San Francisco, (1992) 205-208 [find](https://scholar.google.com/scholar?q=Jain%2C+A%2EN%2E%2C+Waibel%2C+A%2E%2C+Touretzky%2C+D%2ES%2E%3A+Parsec%3A+a+structured+connexionist+parsing+system+for+spoken+language%2E+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing%2C+San+Francisco%2C+%281992)
10. Jamoussi, S., Smaïli, K., Fohr, D., Haton, J.P.: Un système de compréhension automatique de la parole pour l!interrogation orale d!une base de données de bourse, JEP, Fès, Maroc (2004) 281-284 [find](https://scholar.google.com/scholar?q=Jamoussi%2C+S%2E%2C+Sma%C3%AFli%2C+K%2E%2C+Fohr%2C+D%2E%2C+Haton%2C+J%2EP%2E%3A+Un+syst%C3%A8me+de+compr%C3%A9hension+automatique+de+la+parole+pour+l%21interrogation+orale+d%21une+base+de+donn%C3%A9es+de+bourse%2C+JEP%2C+F%C3%A8s%2C+Maroc+%282004%29+281%2D284)
11. Pepelnjak, K., Gros, J., Mihelic, F., Pave"ic, N.: Linguistic Analysis in a Slovenian information retrieval system for flight services. Workshop on Spoken Dialogue Systems, Vigso, Danemark (1995) 65-68 [find](https://scholar.google.com/scholar?q=Pepelnjak%2C+K%2E%2C+Gros%2C+J%2E%2C+Mihelic%2C+F%2E%2C+Pave%22ic%2C+N%2E%3A+Linguistic+Analysis+in+a+Slovenian+information+retrieval+system+for+flight+services%2E+Workshop+on+Spoken+Dialogue+Systems%2C+Vigso%2C+Danemark+%281995%29+65%2D6)
12. Knight, S., Gorell, G., Rayner, M., Milward, D., Koeling, R., Lewin, I.: Comparing grammar-based and robust approaches to speech understanding: a case study. European conference on speech communication and technology, Aalborg, Danemark, (2001) 1779-1782 [find](https://scholar.google.com/scholar?q=Knight%2C+S%2E%2C+Gorell%2C+G%2E%2C+Rayner%2C+M%2E%2C+Milward%2C+D%2E%2C+Koeling%2C+R%2E%2C+Lewin%2C+I%2E%3A+Comparing+grammar%2Dbased+and+robust+approaches+to+speech+understanding%3A+a+case+study%2E+European+conference+on+speech+communicatio)
13. Villaneau, J., Antoine J.Y., Ridoux, O.: Combining Syntax and Pragmatic Knowledge for the Understanding of Spontaneous Spoken Sentences. Logical Aspects of Computational Linguistic, Croisic, France (2001) 279-295 [find](https://scholar.google.com/scholar?q=Villaneau%2C+J%2E%2C+Antoine+J%2EY%2E%2C+Ridoux%2C+O%2E%3A+Combining+Syntax+and+Pragmatic+Knowledge+for+the+Understanding+of+Spontaneous+Spoken+Sentences%2E+Logical+Aspects+of+Computational+Linguistic%2C+Croisic%2C+France+%282)
14. Sadek, D., Bretier, P., Cadoret, V., Cozannet, A., Dupont, P., Ferrieux, A., Panaget, F.: A Cooperative Spoken Dialogue System Based on a Rational Agent Model: A First Implementation on the AGS Application, Workshop on Spoken Dialogue Systems, Vigso, Danemark, (1995) 145-148 [find](https://scholar.google.com/scholar?q=Sadek%2C+D%2E%2C+Bretier%2C+P%2E%2C+Cadoret%2C+V%2E%2C+Cozannet%2C+A%2E%2C+Dupont%2C+P%2E%2C+Ferrieux%2C+A%2E%2C+Panaget%2C+F%2E%3A+A+Cooperative+Spoken+Dialogue+System+Based+on+a+Rational+Agent+Model%3A+A+First+Implementation+on+the+AGS+Applic)
15. Beesely, K.R.: Arabic morphological analysis on the Internet. International Conference on Multi-Lingual Computing, Cambridge (1998) [find](https://scholar.google.com/scholar?q=Beesely%2C+K%2ER%2E%3A+Arabic+morphological+analysis+on+the+Internet%2E+International+Conference+on+Multi%2DLingual+Computing%2C+Cambridge+%281998%29)
16. Ouersighni, R.: A major offshoot of the Dinar-MBC project: AraParse, a morphosyntactic analyzer for unvowelled Arabic texts. ACL/EACL01: Conference of the European Chapter, Workshop: Arabic Language Processing: Status and Prospects (2001) [find](https://scholar.google.com/scholar?q=Ouersighni%2C+R%2E%3A+A+major+offshoot+of+the+Dinar%2DMBC+project%3A+AraParse%2C+a+morphosyntactic+analyzer+for+unvowelled+Arabic+texts%2E+ACL%2FEACL01%3A+Conference+of+the+European+Chapter%2C+Workshop%3A+Arabic+Language+P)
17. Haddad, B., Yaseen, M.: A Compositional Approach Towards Semantic Representation and Construction of ARABIC. LACL, Bordeaux, France (2005) [find](https://scholar.google.com/scholar?q=Haddad%2C+B%2E%2C+Yaseen%2C+M%2E%3A+A+Compositional+Approach+Towards+Semantic+Representation+and+Construction+of+ARABIC%2E+LACL%2C+Bordeaux%2C+France+%282005%29)
18. Meftouh, K., Laskri, M.T. [http://search2.computer.org/advanced/Author_Result.jsp?qtype=3&select=50&qOpt1=DC_CREATOR&sortOrder=d&queryName=Mohamed%20Tayeb%20Laskri:](http://search2.computer.org/advanced/Author_Result.jsp?qtype=3&select=50&qOpt1=DC_CREATOR&sortOrder=d&queryName=Mohamed%20Tayeb%20Laskri:) Generation of the Sense of a Sentence in Arabic Language with a Connectionist Approach, AICCSA'01, Beïrut, Liban (2001). [↗](http://search2.computer.org/advanced/Author_Result.jsp?qtype=3&select=50&qOpt1=DC_CREATOR&sortOrder=d&queryName=Mohamed%20Tayeb%20Laskri:)
19. AL-Johar, B., McGregor, J.: A Logical Meaning Representation for Arabic (LMRA). Proceedings of the 15th National Computer Conference, Riyadh, Saudi Arabia (1997) 31-40 [find](https://scholar.google.com/scholar?q=AL%2DJohar%2C+B%2E%2C+McGregor%2C+J%2E%3A+A+Logical+Meaning+Representation+for+Arabic+%28LMRA%29%2E+Proceedings+of+the+15th+National+Computer+Conference%2C+Riyadh%2C+Saudi+Arabia+%281997%29+31%2D40)
20. Mourad Mars, Mohamed Belgacem, Mounir Zrigui, Georges Antoniadis.: analyseur morphologique pour l'arabe. CITALA 07. Rabat Maroc (2007) [find](https://scholar.google.com/scholar?q=Mourad+Mars%2C+Mohamed+Belgacem%2C+Mounir+Zrigui%2C+Georges+Antoniadis%2E%3A+analyseur+morphologique+pour+l%27arabe%2E+CITALA+07%2E+Rabat+Maroc+%282007%29)
21. Mankaï Naanaa, C.: Compréhension automatique de la langue arabe. Application: Le système Al Biruni. Thèse de l!université de Tunis ,, (1996) [find](https://scholar.google.com/scholar?q=Manka%C3%AF+Naanaa%2C+C%2E%3A+Compr%C3%A9hension+automatique+de+la+langue+arabe%2E+Application%3A+Le+syst%C3%A8me+Al+Biruni%2E+Th%C3%A8se+de+l%21universit%C3%A9+de+Tunis+%2C%2C+%281996%29)
22. Pollard, C., Sag, I.: Head-Driven Phrase Structure Grammar. University of Chicago Press, Chicago (1994) [find](https://scholar.google.com/scholar?q=Pollard%2C+C%2E%2C+Sag%2C+I%2E%3A+Head%2DDriven+Phrase+Structure+Grammar%2E+University+of+Chicago+Press%2C+Chicago+%281994%29)
23. Zouaghi, A., Zrigui, M., Ben Ahmed, M.: A statistical model for semantic decoding of Arabic language statements. Proceedings of NODALIDA, Joensuu, Finland (2005) [find](https://scholar.google.com/scholar?q=Zouaghi%2C+A%2E%2C+Zrigui%2C+M%2E%2C+Ben+Ahmed%2C+M%2E%3A+A+statistical+model+for+semantic+decoding+of+Arabic+language+statements%2E+Proceedings+of+NODALIDA%2C+Joensuu%2C+Finland+%282005%29)
24. Rosenfeld, R.: Adaptive statistical language modelling: A maximum entropy approach. Thesis at Carnegie Mellon University, Pittsburgh, 1994. [find](https://scholar.google.com/scholar?q=Rosenfeld%2C+R%2E%3A+Adaptive+statistical+language+modelling%3A+A+maximum+entropy+approach%2E+Thesis+at+Carnegie+Mellon+University%2C+Pittsburgh%2C+1994%2E)
25. Seneff, S.: Robust parsing for spoken language systems, Proceedings of ICASSP (1992) 189-192 [find](https://scholar.google.com/scholar?q=Seneff%2C+S%2E%3A+Robust+parsing+for+spoken+language+systems%2C+Proceedings+of+ICASSP+%281992%29+189%2D192)
26. Antoine, J-Y., Goulian, J., Villaneau, J.: Quand le TAL robuste s!attaque au langage parlé: analyze incrémentale pour la compréhension de la parole spontanée. Proceedings of TALN, Batz-sur-Mer, France (2003) [find](https://scholar.google.com/scholar?q=Antoine%2C+J%2DY%2E%2C+Goulian%2C+J%2E%2C+Villaneau%2C+J%2E%3A+Quand+le+TAL+robuste+s%21attaque+au+langage+parl%C3%A9%3A+analyze+incr%C3%A9mentale+pour+la+compr%C3%A9hension+de+la+parole+spontan%C3%A9e%2E+Proceedings+of+TALN%2C+Batz%2Dsur%2DMer%2C+France)

*Updated 29 October 2026*