--- title: "Automatic Tagging of Arabic Text — paper by Diab et al. (2004)" description: "The authors build a three-stage pipeline on the Arabic TreeBank (AFP newswire… 95.49% accuracy. 7 references, cited by 92 papers here." authors: ["Mona Diab", "Kadri Hacioglu", "Daniel Jurafsky"] year: 2004 venue: "Proceedings of HLT-NAACL 2004: Short Papers" source: "https://aclanthology.org/N04-4038/" 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/diab-2004-automatic-tagging-arabic-text-raw/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/diab-2004-automatic-tagging-arabic-text-raw/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2004](https://md.research.elamur.ai/free/en/papers/2004/) / Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks # Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks **Authors:** [Mona Diab](https://md.research.elamur.ai/free/en/authors/mona-diab/), [Kadri Hacioglu](https://md.research.elamur.ai/free/en/authors/kadri-hacioglu/) and [Daniel Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/) · **Year:** 2004 · **Venue:** [Proceedings of HLT-NAACL 2004: Short Papers](https://md.research.elamur.ai/free/en/venues/naacl/) ([NAACL 2004](https://md.research.elamur.ai/free/en/venues/naacl/2004/)) · **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/N04-4038/) · [PDF](https://aclanthology.org/N04-4038.pdf) · [OpenAlex](https://openalex.org/W7098814980) **Citations:** 0 citations (OpenAlex, 2026-10-14) · [92](https://md.research.elamur.ai/free/en/papers/diab-2004-automatic-tagging-arabic-text-raw/cited-by/) in our library, of the 141,840 papers whose bibliographies we read ## Summary The paper addresses the lack of fully automatic basic processing tools for Arabic. At the time, clitic segmentation and POS annotation depended on annotators manually choosing among candidate analyses from Buckwalter's AraMorph. The authors build a three-stage pipeline on the Arabic TreeBank (AFP newswire, non-vocalized, Buckwalter transliteration): - **Tokenization:** splitting proclitics and enclitics off stems. - **POS tagging:** using the 24-tag collapsed treebank tagset. - **Base phrase chunking:** finding non-recursive phrases. All three stages are framed as sequence tagging and solved with the same multi-class SVM setup adapted from English work. Only the input units, the context window and the features change between tasks, and no feature is specific to Arabic. The results are: - tokenization F-score of 99.12 - POS accuracy of 95.49% - chunking F-score of 92.08 All three clearly beat simple baselines. When the identical method was trained on English data of similar size, it scored about the same, which supports the claim that the method does not depend on the language. The authors present these as the first reported automatic results for these three Arabic tasks, a practical starting point for parsing and other downstream work. ## Key points - **Data:** the Arabic TreeBank (Arabic Penn TreeBank 1 v2.0) contains 734 AFP articles, about 140k words or 168k tokens. It was split into 4000 training, 119 development and 400 test sentences out of 4519. The setup used an SVM with a degree-2 polynomial kernel and C=1, and scoring used the CoNLL evaluation tools. - **SVM-TOK:** the tokenizer labels each character with one of six segment tags (B-PRE1, B-PRE2, B-WRD, I-WRD, B-SUFF, I-SUFF) using a ±5 character window. It reaches F 99.12, against 88.62 for a rule baseline (RULE) and 93.71 for rules plus a 47,261-entry dictionary from Buckwalter's dictStem (RULE+DICT). The determiner Al is not split off, following treebank practice. - **SVM-POS:** the tagger uses a ±2 token window with character n-grams and a token type feature (alphabetic or numeric). It achieves 95.49% accuracy versus 92.2% for a most-frequent-tag baseline. About half of its errors are NN/JJ confusions, partly caused by inconsistent gold annotation. - **SVM-BP:** the chunker covers 9 phrase types with IOB labels (19 classes), using training data produced by flattening treebank trees with ChunkLink. It scores F 92.08 overall, with VP at 97.6 and PP at 98.4. - **English controls:** the same tagger and chunker trained on English data of matched size reached 94.97% POS accuracy and chunking F 93.05. ## Interesting ideas - **Segmentation as character-level BIO tagging.** Morphological segmentation becomes an ordinary sequence-labeling task with no handcrafted analyzer. This could transfer to other clitic-heavy or agglutinative languages, including splitting Ukrainian particles or handling compounds. - **One learner, three tasks.** A single classifier setup serves every level, with only the inputs, window and features changing. This makes the pipeline cheap to build and maintain, and easy to port to a new language once a treebank exists. - **Matched-size cross-language control.** The authors retrained on English with the same amount of data to judge whether the Arabic scores are good. This gives a fairer reference point than comparing against English systems trained on much larger corpora. - **Deriving chunk data from existing trees.** Flattening treebank trees into chunk labels (here with ChunkLink) yields chunking training data without any new annotation effort. - **Error analysis that checks the gold data.** Tracing the NN/JJ errors back to inconsistent gold labels shows that part of the remaining error lies in the annotation, not the model. This kind of check is worth doing before spending effort on model tuning. *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/) · 9,086 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,889 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works 🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 1,484 works ## Cite Cite as: Mona Diab, Kadri Hacioglu and Daniel Jurafsky. 2004. Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks. Proceedings of HLT-NAACL 2004: Short Papers. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{diab2004automatic, title = {{Automatic Tagging of Arabic Text: From Raw Text to Base Phrase Chunks}}, author = {Mona Diab, Kadri Hacioglu and Daniel Jurafsky}, booktitle = {Proceedings of HLT-NAACL 2004: Short Papers}, year = {2004}, url = {https://aclanthology.org/N04-4038/} } ``` - [← previous A Rule Based Approach to Discourse Parsing](https://md.research.elamur.ai/free/en/papers/polanyi-2004-rule-based-approach-discourse-parsing/) - [next → Inferring Sentence-internal Temporal Relations](https://md.research.elamur.ai/free/en/papers/lapata-2004-inferring-sentence-internal-temporal-relations/) - [↑ back to papers of 2004](https://md.research.elamur.ai/free/en/papers/2004/) ## References 7 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Erin L. Allwein, Robert E. Schapire, and Yoram Singer. 2000. Reducing multiclass to binary: A unifying approach for margin classifiers. Journal of Machine Learning Research, 1:113-141. [find](https://scholar.google.com/scholar?q=Erin+L%2E+Allwein%2C+Robert+E%2E+Schapire%2C+and+Yoram+Singer%2E+2000%2E+Reducing+multiclass+to+binary%3A+A+unifying+approach+for+margin+classifiers%2E+Journal+of+Machine+Learning+Research%2C+1%3A113%2D141%2E) 2. Kadri Hacioglu and Wayne Ward. 2003. Target word Detection and semantic role chunking using support vector machines. HLT-NAACL 2003. [find](https://scholar.google.com/scholar?q=Kadri+Hacioglu+and+Wayne+Ward%2E+2003%2E+Target+word+Detection+and+semantic+role+chunking+using+support+vector+machines%2E+HLT%2DNAACL+2003%2E) 3. Thorsten Joachims. 1998. [Text Categorization with Support Vector Machines: Learning with Many Relevant Features](https://md.research.elamur.ai/free/en/papers/joachims-1998-text-categorization-support-vector-machines/). Proc. of ECML-98, 10th European Conf. on Machine Learning. [↗](https://doi.org/10.17877/de290r-5097) 4. Shereen Khoja. 2001. APT: Arabic Part-of-speech Tagger. Proc. of the Student Workshop at NAACL 2001. [find](https://scholar.google.com/scholar?q=Shereen+Khoja%2E+2001%2E+APT%3A+Arabic+Part%2Dof%2Dspeech+Tagger%2E+Proc%2E+of+the+Student+Workshop+at+NAACL+2001%2E) 5. Taku Kudo and Yuji Matsumato. 2000. Use of support vector learning for chunk identification. Proc. of the 4th Conf. on Very Large Corpora, pages 142-144. [find](https://scholar.google.com/scholar?q=Taku+Kudo+and+Yuji+Matsumato%2E+2000%2E+Use+of+support+vector+learning+for+chunk+identification%2E+Proc%2E+of+the+4th+Conf%2E+on+Very+Large+Corpora%2C+pages+142%2D144%2E) 6. Erik Tjong, Kim Sang, and Sabine Buchholz. 2000. [Introduction to the CoNLL-2000 shared task: Chunking](https://md.research.elamur.ai/free/en/papers/sang-2000-introduction-conll-2000-shared-task/). Proc. of the 4th Conf. on Computational Natural Language Learning (CoNLL), Lisbon, Portugal, 2000, pp. 127-132. 7. Vladamir Vapnik. 1995. The Nature of Statistical Learning Theory. Springer Verlag, New York, USA. [↗](https://doi.org/10.1007/978-1-4757-2440-0) *Updated 24 October 2026*