---
title: "The Impact of Morphological Stemming on Arabic Mention"
description: "The authors build an Entity Detection and Recognition (EDR) system for the ACE 2004 Arabic data… 22 references, cited by 13 papers here."
authors: ["Imed Zitouni", "Jeffrey Sorensen", "Xiaoqiang Luo", "Radu Florian"]
year: 2005
venue: "Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages"
source: "https://aclanthology.org/W05-0709/"
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/zitouni-2005-impact-morphological-stemming-arabic-mention/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zitouni-2005-impact-morphological-stemming-arabic-mention/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2005](https://md.research.elamur.ai/free/en/papers/2005/) / The Impact of Morphological Stemming on Arabic Mention Detection and Coreference Resolution

# The Impact of Morphological Stemming on Arabic Mention Detection and Coreference Resolution

**Authors:** [Imed Zitouni](https://md.research.elamur.ai/free/en/authors/imed-zitouni/), [Jeffrey Sorensen](https://md.research.elamur.ai/free/en/authors/jeffrey-sorensen/), [Xiaoqiang Luo](https://md.research.elamur.ai/free/en/authors/xiaoqiang-luo/) and [Radu Florian](https://md.research.elamur.ai/free/en/authors/radu-florian/) · **Year:** 2005 · **Venue:** [Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages](https://md.research.elamur.ai/free/en/venues/acl-workshop-on-computational-approaches-to-semitic-languages/) ([ACL Workshop on Computational Approaches to Semitic Languages 2005](https://md.research.elamur.ai/free/en/venues/acl-workshop-on-computational-approaches-to-semitic-languages/2005/)) · **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/W05-0709/) · [PDF](https://aclanthology.org/W05-0709.pdf) · [OpenAlex](https://openalex.org/W1977830583)

**Citations:** 45 citations (OpenAlex, 2026-10-14) · [13](https://md.research.elamur.ai/free/en/papers/zitouni-2005-impact-morphological-stemming-arabic-mention/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Arabic attaches articles, prepositions, conjunctions and pronouns directly to words, so one whitespace-delimited token may hold several mentions, such as a noun and a possessive pronoun that point to different entities. The authors build an Entity Detection and Recognition (EDR) system for the ACE 2004 Arabic data that first splits words into prefixes, stems and suffixes.

The segmenter chains three finite-state machines:
- affix-expansion rules that produce a lattice of candidate splits,
- a stem dictionary,
- a Kneser-Ney trigram language model, plus a character-level model for unknown words.

A weaker character n-gram segmenter auto-segments part of Arabic Gigaword, which enlarges the stem vocabulary. The segments then feed two maximum-entropy components: a cascaded mention detector that uses stem, prefix and suffix n-gram features, and a coreference resolver with stem-matching features.

Stem features mostly raise recall in mention detection and add about 2 F-points to coreference. The data partition is clearly documented, and the system ranked among the top ACE 2004 participants. The work shows that subword segmentation is a basic requirement for entity tracking in agglutinative languages.

## Key points
- The dictionary-based segmenter was trained on about 0.5M words from Arabic Treebanks 1V2, 2V2 and 3V1 and reaches 97.8% exact word-match segmentation. The character n-gram model alone gets 94.5%, but it handles unseen words better.
- Bootstrapped vocabulary: a stem or affix is kept if it has a frequency above two in the supervised data, or a frequency above ten in the auto-segmented Gigaword portion. This gives roughly 53K entries, about six times the supervised vocabulary.
- Mention detection: stem n-gram features improve first-level classification mainly through recall, with precision nearly unchanged. Full-cascade F-measure moves only from 59.4 to 59.7. Dropping the prefix/suffix n-gram features barely matters.
- Coreference with stem features:

  | Mentions | Metric | Base | Base+Stem |
  |---|---|---|---|
  | True mentions | ECM-F | 77.7 | 80.0 |
  | True mentions | ACE-Value | 86.9 | 88.2 |
  | System mentions | ECM-F | 62.3 | 64.2 |
  | System mentions | ACE-Value | 61.9 | 63.1 |

  ACE-Value gains are smaller because that metric weights names heavily and discounts pronouns.
- Affix information acts as a hard constraint: mentions that disagree in gender or number are never chained.

## Interesting ideas
- Let a less accurate model that generalizes well to unseen words label a large raw corpus, then admit only frequent items into the precise dictionary model, with a stricter threshold for silver data than for gold.
- Build segmentation as a composition of transducers (affix rules → candidate lattice, dictionary, n-gram scorer) with an explicit, penalized unknown-word path.
- In coreference, match mentions on stems rather than surface strings, and veto links between mentions whose morphological agreement features conflict.
- Score coreference twice, on gold mentions and on system-detected mentions, and with two metrics, explaining any gap by how each metric weights mention types.
- Treat a pronoun buried inside a word as its own mention that must not corefer with its host word.

## For Mova

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

- **I1** (learn): Silver output agreed by witness parsers could grow lexicons or repair-rule inventories only past a frequency bar set higher than the one for gold treebank material.
- **I2** (tokens): Splitting English clitics and contractions ('s, n't, 'll) could keep every candidate in a lattice, so the chosen split stays explainable instead of hard-coded.
- **I3** (frames): Coreference could compare lemmas from crate en (company/companies) and use number/gender from morphology as hard filters before any scoring.
- **I4** (learn): Evaluations could separate upstream detection errors from linking errors and check whether a gain holds under pronoun-sensitive and name-weighted metrics.
- **I5** (world): When building entities, possessive determiners in phrases like "their company" should spawn a separate entity reference that is never merged with the noun it attaches to.

*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

- [IBM](https://md.research.elamur.ai/free/en/companies/ibm/) — Company, Armonk, United States · 139 works · 70,691 citations
- [IBM Research - Thomas J. Watson Research Center](https://md.research.elamur.ai/free/en/labs/ibm-research-thomas-j-watson-research-center/) — Research institute, Yorktown Heights, United States · 53 works · 49,193 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 (3): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [🔗 Coreference resolution](https://md.research.elamur.ai/free/en/topics/coreference-resolution/) · 574 works · [🧩 Morphology](https://md.research.elamur.ai/free/en/topics/morphology/) · 405 works

## Cite

Cite as: Imed Zitouni, Jeffrey Sorensen, Xiaoqiang Luo and Radu Florian. 2005. The Impact of Morphological Stemming on Arabic Mention Detection and Coreference Resolution. Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages.

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

```bibtex
@inproceedings{zitouni2005impact,
  title = {{The Impact of Morphological Stemming on Arabic Mention Detection and Coreference Resolution}},
  author = {Imed Zitouni, Jeffrey Sorensen, Xiaoqiang Luo and Radu Florian},
  booktitle = {Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages},
  year = {2005},
  doi = {10.3115/1621787.1621800},
  url = {https://doi.org/10.3115/1621787.1621800}
}
```

- [← previous A Framework for Annotating Information Structure in Discourse](https://md.research.elamur.ai/free/en/papers/calhoun-2005-framework-annotating-information-structure-discourse/)
- [next → Dialogue Act Tagging for Instant Messaging Chat Sessions](https://md.research.elamur.ai/free/en/papers/ivanovic-2005-dialogue-act-tagging-instant-messaging/)
- [↑ back to papers of 2005](https://md.research.elamur.ai/free/en/papers/2005/)

## References

22 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Peter F. Abbou and Ernest N. McCarus, editors. 1983. Elementary modern standard Arabic. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Peter+F%2E+Abbou+and+Ernest+N%2E+McCarus%2C+editors%2E+1983%2E+Elementary+modern+standard+Arabic%2E+Cambridge+University+Press%2E)
2. ACE. 2004. Automatic content extraction. [http://www.ldc.upenn.edu/Projects/ACE/](http://www.ldc.upenn.edu/Projects/ACE/). [↗](http://www.ldc.upenn.edu/Projects/ACE/)
3. Joan Aliprand, Julie Allen, Joe Becker, Mark Davis, Michael Everson, Asmus Freytag, John Jenkins, Mike Ksar, Rick McGowan, Eric Muller, Lisa Moore, Michel Suignard, and Ken Whistler. 2004. The unicode standard. [http://www.unicode.org/](http://www.unicode.org/). [↗](http://www.unicode.org/)
4. A. Berger, S. Della Pietra, and V. Della Pietra. 1996. [A maximum entropy approach to natural language processing](https://md.research.elamur.ai/free/en/papers/berger-1996-maximum-entropy-approach-natural-language/). Computational Linguistics, 22(1):39–71. [↗](https://doi.org/10.5555/234285.234289)
5. D. M. Bikel, S. Miller, R. Schwartz, and R. Weischedel. 1997. [Nymble: a high-performance learning name-finder](https://md.research.elamur.ai/free/en/papers/bikel-1997-nymble-high-performance-learning-name/). In Proceedings of ANLP-97, pages 194–201. [↗](https://doi.org/10.48550/arxiv.cmp-lg/9803003)
6. A. Borthwick. 1999. A Maximum Entropy Approach to Named Entity Recognition. Ph.D. thesis, New York University. [find](https://scholar.google.com/scholar?q=A%2E+Borthwick%2E+1999%2E+A+Maximum+Entropy+Approach+to+Named+Entity+Recognition%2E+Ph%2ED%2E+thesis%2C+New+York+University%2E)
7. Egyptian Demographic Center. 2000. [http://www.frcu.eun.eg/www/homepage/cdc/cdc.htm](http://www.frcu.eun.eg/www/homepage/cdc/cdc.htm). [↗](http://www.frcu.eun.eg/www/homepage/cdc/cdc.htm)
8. Aitao Chen and Fredic Gey. 2002. Building an arabic stemmer for information retrieval. In Proceedings of the Eleventh Text REtrieval Conference (TREC 2002), National Institute of Standards and Technology, November. [find](https://scholar.google.com/scholar?q=Aitao+Chen+and+Fredic+Gey%2E+2002%2E+Building+an+arabic+stemmer+for+information+retrieval%2E+In+Proceedings+of+the+Eleventh+Text+REtrieval+Conference+%28TREC+2002%29%2C+National+Institute+of+Standards+and+Technol)
9. S. F. Chen and J. Goodman. 1998. An empirical study of smoothing techinques for language modeling. Technical Report TR-10-98, Center for Research in Computing Technology, Harvard University, Cambridge, Massachusettes, August. [find](https://scholar.google.com/scholar?q=S%2E+F%2E+Chen+and+J%2E+Goodman%2E+1998%2E+An+empirical+study+of+smoothing+techinques+for+language+modeling%2E+Technical+Report+TR%2D10%2D98%2C+Center+for+Research+in+Computing+Technology%2C+Harvard+University%2C+Cambridge)
10. R. Florian, H. Hassan, A. Ittycheriah, H. Jing, N. Kambhatla, X. Luo, N Nicolov, and S Roukos. 2004. [A statistical model for multilingual entity detection and tracking](https://md.research.elamur.ai/free/en/papers/florian-2004-statistical-model-multilingual-entity-detection/). In Proceedings of HLT-NAACL 2004, pages 1–8. [↗](https://doi.org/10.21236/ada460245)
11. Y.-S. Lee, K. Papineni, S. Roukos, O. Emam, and H. Hassan. 2003. [Language model based Arabic word segmentation](https://md.research.elamur.ai/free/en/papers/lee-2003-language-model-based-arabic-word/). In Proceedings of the ACL’03, pages 399–406.
12. Xiaoqiang Luo, Abe Ittycheriah, Hongyan Jing, Nanda Kambhatla, and Salim Roukos. 2004. [A mention-synchronous coreference resolution algorithm based on the bell tree](https://md.research.elamur.ai/free/en/papers/luo-2004-mention-synchronous-coreference-resolution-algorithm/). In Proc. of ACL’04.
13. A. Mikheev, M. Moens, and C. Grover. 1999. [Named entity recognition without gazetteers](https://md.research.elamur.ai/free/en/papers/mikheev-1999-named-entity-recognition-without-gazetteers/). In Proceedings of EACL’99.
14. S. Miller, M. Crystal, H. Fox, L. Ramshaw, R. Schwarz, R. Stone, and R. Weischedel. 1998. Bbn: Description of the SIFT system as used for MUC-7. In MUC-7. [find](https://scholar.google.com/scholar?q=S%2E+Miller%2C+M%2E+Crystal%2C+H%2E+Fox%2C+L%2E+Ramshaw%2C+R%2E+Schwarz%2C+R%2E+Stone%2C+and+R%2E+Weischedel%2E+1998%2E+Bbn%3A+Description+of+the+SIFT+system+as+used+for+MUC%2D7%2E+In+MUC%2D7%2E)
15. V. Ng and C. Cardie. 2002. [Improving machine learning approaches to coreference resolution](https://md.research.elamur.ai/free/en/papers/ng-2002-improving-machine-learning-approaches-coreference/). In Proceedings of the ACL’02, pages 104–111.
16. NIST. 2004. Proceedings of ace evaluation and pi meeting 2004 workshop. Alexandria, VA, September. NIST. [find](https://scholar.google.com/scholar?q=NIST%2E+2004%2E+Proceedings+of+ace+evaluation+and+pi+meeting+2004+workshop%2E+Alexandria%2C+VA%2C+September%2E+NIST%2E)
17. W. M. Soon, H. T. Ng, and C. Y. Lim. 2001. [A machine learning approach to coreference resolution of noun phrases](https://md.research.elamur.ai/free/en/papers/soon-2001-machine-learning-approach-coreference-resolution/). Computational Linguistics, 27(4):521–544. [↗](https://doi.org/10.1162/089120101753342653)
18. R. Sproat, C. Shih, W. Gale, and N. Chang. 1996. [A stochastic finite-state word-segmentation algorithm for Chinese](https://md.research.elamur.ai/free/en/papers/sproat-1996-stochastic-finite-state-word-segmentation/). Computational Linguistics, 22(3).
19. M. Tayli and A. Al-Salamah. 1990. Building bilingual microcomputer systems. Communications of the ACM, 33(5):495–505. [find](https://scholar.google.com/scholar?q=M%2E+Tayli+and+A%2E+Al%2DSalamah%2E+1990%2E+Building+bilingual+microcomputer+systems%2E+Communications+of+the+ACM%2C+33%285%29%3A495%E2%80%93505%2E)
20. J. Wightwick and M. Gaafar. 1998. Arabic Verbs and Essentials of Grammar. Passport Books. [find](https://scholar.google.com/scholar?q=J%2E+Wightwick+and+M%2E+Gaafar%2E+1998%2E+Arabic+Verbs+and+Essentials+of+Grammar%2E+Passport+Books%2E)
21. J. Xu, A. Fraser, and R. Weischedel. 2001. Trec2001 cross-lingual retrieval at bbn. In TREC 2001, Gaithersburg: NIST. [find](https://scholar.google.com/scholar?q=J%2E+Xu%2C+A%2E+Fraser%2C+and+R%2E+Weischedel%2E+2001%2E+Trec2001+cross%2Dlingual+retrieval+at+bbn%2E+In+TREC+2001%2C+Gaithersburg%3A+NIST%2E)
22. J. Xu, A. Fraser, and R. Weischedel. 2002. Empirical studies in strategies for arabic information retrieval. In SIGIR 2002, Tampere, Finland. [find](https://scholar.google.com/scholar?q=J%2E+Xu%2C+A%2E+Fraser%2C+and+R%2E+Weischedel%2E+2002%2E+Empirical+studies+in+strategies+for+arabic+information+retrieval%2E+In+SIGIR+2002%2C+Tampere%2C+Finland%2E)

*Updated 1 November 2026*