[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/aclbulk-2012-hulden-conversion-procedural-morphologies-finite-state/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [Semitic languages](https://md.mova.elamur.ai/free/en/docs/papers/sem/) / Conversion of Procedural Morphologies to Finite-State Morphologies: A Case Study of Arabic

# Conversion of Procedural Morphologies to Finite-State Morphologies: A Case Study of Arabic

**Authors:** [Mans Hulden](https://md.mova.elamur.ai/free/en/docs/papers/authors/mans-hulden/); [Younes Samih](https://md.mova.elamur.ai/free/en/docs/papers/authors/younes-samih/) · **Year:** 2012 · **Venue:** Proceedings of the 10th International Workshop on Finite State Methods and NLP (FSMNLP 2012), pp. 70–74 **Link:** [aclanthology.org/W12-6213](https://aclanthology.org/W12-6213/) · library `aclbulk-2012-hulden-conversion-procedural-morphologies-finite-state` · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) (ACL Anthology, before 2016) — summary only

[**1** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/aclbulk-2012-hulden-conversion-procedural-morphologies-finite-state/) of the 140673 papers whose bibliographies we read[Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing](https://aclanthology.org/volumes/W12-62/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/)

- [Publisher's page](https://aclanthology.org/W12-6213/)
- [PDF](https://aclanthology.org/W12-6213.pdf)

**Authors (2)**

1. Mans Hulden
2. Younes Samih

Citations and author metrics from OpenAlex (); authors with the same name are not always told apart.

## What it is about

The Buckwalter Arabic Morphological Analyzer is a Perl program that splits a word into prefix, stem and suffix, checks the pieces against three lexicons and three co-occurrence tables, and retries with spelling variants when lookup fails. The authors convert it, one-to-one, into a finite-state transducer built with the foma compiler, and then add extensions that are hard in the procedural code: partially vocalized input is handled without overgeneration, and the same transducer also generates. The lexicon is built with vocalized morphemes and the vowels are deleted optionally on the surface. Composing the constraint rules one at a time keeps the intermediate size small, where a single intersection would grow exponentially. The result has 855,267 states and 1,907,978 arcs, accepts about 14.6 billion surface forms, and takes 8.5 MB, against 4.0 MB for the original files; the paper also reports that some co-occurrence constraints are redundant and can be found by counting paths.

## Ideas

- I1. Compile the segmenter's tables into one finite-state lexicon, with the compatibility rules composed in one at a time rather than intersected at once. For `tools/hbo` this means the prefix, stem and suffix tables learned from MACULA become a transducer, and the composition order is recorded and measured by state count.
- I2. Keep the lexicon fully pointed and delete the vowels optionally on the surface, so that one table serves both the pointed and the unpointed mode of `tools/hbo`. This removes a second table that has to be kept in step with the first.
- I3. Find redundant constraints by counting paths: a rule that removes no paths is subsumed by an earlier rule. Run this count on the `pre` and `suf` tables of `tools/hbo` and report which rules can go.

## For Mova

I1 and I3 are design notes for `tools/hbo` (the segmenter tables `lex`, `pre` and the rest). I2 is the pointed/unpointed split of the same tool, and the script facts it relies on belong in [1. Script and pointing](https://md.mova.elamur.ai/free/en/docs/languages/hbo/01-script/). The Arabic-specific alif normalization is not needed for Hebrew.

## Cite

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

```
@inproceedings{hulden2012conversion,
  title = {{Conversion of Procedural Morphologies to Finite-State Morphologies: A Case Study of Arabic}},
  author = {Hulden, Mans and Samih, Younes},
  booktitle = {Proceedings of the 10th International Workshop on Finite State Methods and Natural Language Processing},
  year = {2012},
  url = {https://aclanthology.org/W12-6213/}
}
```

- [← previous Identifying Broken Plurals, Irregular Gender, and Rationality in Arabic Text](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2012-alkuhlani-identifying-broken-plurals-irregular-gender/)
- [next → Unsupervised Morphology Rivals Supervised Morphology for Arabic MT](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2012-stallard-unsupervised-morphology-rivals-supervised-morphology/)
- [↑ back to Semitic languages](https://md.mova.elamur.ai/free/en/docs/papers/sem/)

## References

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

1. Attia, M., Pecina, P., Toral, A., Tounsi, L., and van Genabith, J. (2011). An open-source finite state morphological transducer for modern standard Arabic. In Proceedings of the 9th International Workshop on Finite State Methods and Natural Language Processing, pages 125–133. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Attia%2C+M%2E%2C+Pecina%2C+P%2E%2C+Toral%2C+A%2E%2C+Tounsi%2C+L%2E%2C+and+van+Genabith%2C+J%2E+%282011%29%2E+An+open%2Dsource+finite+state+morphological+transducer+for+modern+standard+Arabic%2E+In+Proceedings+of+the+9th+International+Work) [our card](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2011-attia-open-source-finite-state-morphological/)
2. Beesley, K. R. (1996). Arabic finite-state morphological analysis and generation. In Proceedings of COLING’96—Volume 1, pages 89–94. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Beesley%2C+K%2E+R%2E+%281996%29%2E+Arabic+finite%2Dstate+morphological+analysis+and+generation%2E+In+Proceedings+of+COLING%E2%80%9996%E2%80%94Volume+1%2C+pages+89%E2%80%9394%2E+Association+for+Computational+Linguistics%2E)
3. Beesley, K. R. and Karttunen, L. (2003). Finite State Morphology. CSLI Publications, Stanford, CA. [find](https://scholar.google.com/scholar?q=Beesley%2C+K%2E+R%2E+and+Karttunen%2C+L%2E+%282003%29%2E+Finite+State+Morphology%2E+CSLI+Publications%2C+Stanford%2C+CA%2E)
4. Buckwalter, T. (2004). Arabic Morphological Analyzer 2.0. Linguistics Data Consortium (LDC). [find](https://scholar.google.com/scholar?q=Buckwalter%2C+T%2E+%282004%29%2E+Arabic+Morphological+Analyzer+2%2E0%2E+Linguistics+Data+Consortium+%28LDC%29%2E)
5. Habash, N. (2010). Introduction to Arabic natural language processing. Synthesis Lectures on Human Language Technologies. [find](https://scholar.google.com/scholar?q=Habash%2C+N%2E+%282010%29%2E+Introduction+to+Arabic+natural+language+processing%2E+Synthesis+Lectures+on+Human+Language+Technologies%2E)
6. Halácsy, P., Kornai, A., Németh, L., Rung, A., Sza-kadát, I., and Trón, V. (2004). Creating open language resources for Hungarian. In Proceedings of Language Resources and Evaluation Conference (LREC04). European Language Resources Association. [find](https://scholar.google.com/scholar?q=Hala%CC%81csy%2C+P%2E%2C+Kornai%2C+A%2E%2C+Ne%CC%81meth%2C+L%2E%2C+Rung%2C+A%2E%2C+Sza%2Dkada%CC%81t%2C+I%2E%2C+and+Tro%CC%81n%2C+V%2E+%282004%29%2E+Creating+open+language+resources+for+Hungarian%2E+In+Proceedings+of+Language+Resources+and+Evaluation+Conference+%28L)
7. Hulden, M. (2009a). Fast approximate string matching with finite automata. Procesamiento del lenguaje natural, 43:57–64. [find](https://scholar.google.com/scholar?q=Hulden%2C+M%2E+%282009a%29%2E+Fast+approximate+string+matching+with+finite+automata%2E+Procesamiento+del+lenguaje+natural%2C+43%3A57%E2%80%9364%2E)
8. Hulden, M. (2009b). Foma: a finite-state compiler and library. In Proceedings of the 12th conference of the European Chapter of the Association for Computational Linguistics,, pages 29–32. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Hulden%2C+M%2E+%282009b%29%2E+Foma%3A+a+finite%2Dstate+compiler+and+library%2E+In+Proceedings+of+the+12th+conference+of+the+European+Chapter+of+the+Association+for+Computational+Linguistics%2C%2C+pages+29%E2%80%9332%2E+Association)
9. Kaplan, R. M. (1987). Three seductions of computational psycholinguistics. In Whitelock, P., Wood, M. M., Somers, H. L., Johnson, R., and Bennett, P., editors, Linguistic Theory and Computer Applications, London. Academic Press. [find](https://scholar.google.com/scholar?q=Kaplan%2C+R%2E+M%2E+%281987%29%2E+Three+seductions+of+computational+psycholinguistics%2E+In+Whitelock%2C+P%2E%2C+Wood%2C+M%2E+M%2E%2C+Somers%2C+H%2E+L%2E%2C+Johnson%2C+R%2E%2C+and+Bennett%2C+P%2E%2C+editors%2C+Linguistic+Theory+and+Computer+Applicati)
10. Pirinen, T., Lindén, K., et al. (2010). Finite-state spell-checking with weighted language and error models. In Proceedings of LREC 2010 Workshop on creation and use of basic lexical resources for less-resourced languages. [find](https://scholar.google.com/scholar?q=Pirinen%2C+T%2E%2C+Linde%CC%81n%2C+K%2E%2C+et+al%2E+%282010%29%2E+Finite%2Dstate+spell%2Dchecking+with+weighted+language+and+error+models%2E+In+Proceedings+of+LREC+2010+Workshop+on+creation+and+use+of+basic+lexical+resources+for+le)