--- title: "Discovering Lexical Information by Tagging Arabic Newspaper Text" description: "Abuleil and Evens address the lack of a large Arabic lexicon. 19 references, cited by 3 papers here." authors: ["Saleem Abuleil", "Martha Evens"] year: 1998 venue: "Computational Approaches to Semitic Languages" source: "https://aclanthology.org/W98-1001/" 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/abuleil-1998-discovering-lexical-information-tagging-arabic/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/abuleil-1998-discovering-lexical-information-tagging-arabic/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [1998](https://md.research.elamur.ai/free/en/papers/1998/) / Discovering Lexical Information by Tagging Arabic Newspaper Text # Discovering Lexical Information by Tagging Arabic Newspaper Text **Authors:** [Saleem Abuleil](https://md.research.elamur.ai/free/en/authors/saleem-abuleil/) and [Martha Evens](https://md.research.elamur.ai/free/en/authors/martha-evens/) · **Year:** 1998 · **Venue:** Computational Approaches to Semitic Languages · **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/W98-1001/) · [PDF](https://aclanthology.org/W98-1001.pdf) · [OpenAlex](https://openalex.org/W1999914225) **Citations:** 25 citations (OpenAlex, 2026-10-14) · [3](https://md.research.elamur.ai/free/en/papers/abuleil-1998-discovering-lexical-information-tagging-arabic/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary Abuleil and Evens address the lack of a large Arabic lexicon. Their approach is to grow one automatically while tagging newspaper text. Arabic makes this hard in three ways: there is no capitalization to signal names, short vowels are usually omitted (so one spelling can be a noun or a verb), and prepositions or articles can be glued onto the front of words. The system was tested on a corpus of Al-Raya (Qatar) articles. It has four parts: a tokenizer that splits off attached particles, a morphology analyzer, a Type-Finder and a Feature-Finder. All of them work around a seed lexicon that the system keeps extending. The Type-Finder runs a series of tests in order: lexicon lookup, phrase grammar rules, high-certainty affix rules, and finally word patterns checked against weaker affix evidence. Proper nouns are found through classified trigger keywords and typed grammar rules. The paper reports no accuracy figures. Its value is a transparent, rule-based design for bootstrapping a lexicon in a morphologically rich, unvowelized language. ## Key points - The corpus is Al-Raya newspaper text assembled by Ahmad Hasnah (1996). The seed lexicon was hand-built by Khalid Alsamara (1996), with a main table linked to tables for verbs, nouns and particles, plus new tables for proper nouns. - The tokenizer sorts Arabic words into eight classes by their prefix behaviour. It then strips punctuation and attached particles according to that class. - The authors collected 163 morphological patterns and labelled each as noun-only, verb-only, or both. - Affix cues are divided into rule (A), which decides the category with certainty, and rule (B), which is usually right. A rule (B) result only counts when a lookup table combines it with the pattern evidence. - Proper nouns fall into these classes, each with its own attribute slots: personal names, organizations, political and natural locations, times, products, events, and categories such as nationality, language or religion. They are detected through keywords like titles, job titles, "University", "State of", "Lake" and "Month of". ## Interesting ideas - Tag unknown words with an ordered chain of tests that runs from the most reliable to the least reliable and stops at the first one that succeeds, so every tag carries a record of which test produced it. - Grade morphological cues by strength: decisive cues settle the tag alone, while merely suggestive cues may only confirm or break ties with another signal through an explicit combination table. - Let a trigger word next to an unknown name pass its semantic type and gender to the name through feature agreement in a small grammar rule, e.g. a feminine title marks the following name as a female person. - Give each proper-noun class its own attribute slots, such as occupation, nationality and organization for people, or type and location for places, and fill them from the surrounding text. - Treat the lexicon as a living store that the tagger updates while it processes text, so later sentences benefit from what earlier ones revealed. ## For Mova How these ideas could serve Mova, our small open language model — its files, stages and tests: - **I1** (tokens): The en tagger's fallback for out-of-lexicon words could use such a cascade (lexicon, phrase context, decisive suffix, weak suffix plus shape) and expose the deciding step as its explanation. - **I2** (tokens): English suffixes like "-ness" (decisive) versus "-s" or "-ed" (suggestive) could be encoded this way, which avoids silent overconfidence from weak cues in morphology. - **I3** (frames): Coreference could use title-derived gender and type ("Mrs.", "Lake", "University of") as explainable constraints when linking pronouns and definite descriptions to newly met names. - **I4** (world): Entity records in the world of a text could start from class-specific slot templates filled from appositions and modifiers, giving holdings and states a typed frame from the first mention. - **I5** (learn): New lexical entries induced while reading could go into a provisional layer and be promoted only after several witness parsers agree, which keeps self-extension auditable. *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 - [Illinois Institute of Technology](https://md.research.elamur.ai/free/en/universities/illinois-institute-of-technology/) — University, Chicago, United States · 12 works · 1,006 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 (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works ## Cite Cite as: Saleem Abuleil and Martha Evens. 1998. Discovering Lexical Information by Tagging Arabic Newspaper Text. Computational Approaches to Semitic Languages. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{abuleil1998discovering, title = {{Discovering Lexical Information by Tagging Arabic Newspaper Text}}, author = {Saleem Abuleil and Martha Evens}, booktitle = {Computational Approaches to Semitic Languages}, year = {1998}, doi = {10.3115/1621753.1621755}, url = {https://doi.org/10.3115/1621753.1621755} } ``` - [← previous Lexical marking of discourse relations - some experimental findings](https://md.research.elamur.ai/free/en/papers/soria-1998-lexical-marking-discourse-relations-some/) - [next → Computing Dialogue Acts from Features with Transformation-Based Learning](https://md.research.elamur.ai/free/en/papers/samuel-1998-computing-dialogue-acts-features-transformation/) - [↑ back to papers of 1998](https://md.research.elamur.ai/free/en/papers/1998/) ## References 19 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Abu-Salem, H., 1992, A Microcomputer Based Arabic Bibliography Information Retrieval System v, ith Relational Thesauri (Arabic-IRS). Unpublished Ph.D. Dissertation, Computer Science Department, Illinois Institute of Technology, Chicago, IL. [find](https://scholar.google.com/scholar?q=Abu%2DSalem%2C+H%2E%2C+1992%2C+A+Microcomputer+Based+Arabic+Bibliography+Information+Retrieval+System+v%2C+ith+Relational+Thesauri+%28Arabic%2DIRS%29%2E+Unpublished+Ph%2ED%2E+Dissertation%2C+Computer+Science+Department%2C+Illino) 2. Ahlswede, T.E., and Evens, M., 1988, "Generating a Relational Lexicon from a Machine Readable Dictionary", International Joumal of Lexicography, Vol. 1, No. 3, pp. 214-237. [↗](https://doi.org/10.1093/ijl/1.3.214) 3. Alsamara, K., 1996. An Arabic Lexicon To Support Information Retrieval, Parsing, and Text Generation. Unpublished Ph.D. Dissertation, Illinois Institute of Technology, Chicago, IL. [find](https://scholar.google.com/scholar?q=Alsamara%2C+K%2E%2C+1996%2E+An+Arabic+Lexicon+To+Support+Information+Retrieval%2C+Parsing%2C+and+Text+Generation%2E+Unpublished+Ph%2ED%2E+Dissertation%2C+Illinois+Institute+of+Technology%2C+Chicago%2C+IL%2E) 4. Brill, E., 1992. "[A Simple Rule-based Part of Speech Tagger](https://md.research.elamur.ai/free/en/papers/brill-1992-simple-rule-based-part-speech/)". Proceedings of the 3rd Conference on Applied Natural Language Processing, Trento, Italy, pp. 152-155. 5. Cowie, J., and Lehnert, W., 1996. "Information Extraction", Communications of the ACM, Vol. 39, No. 1, pp. 83-92. [find](https://scholar.google.com/scholar?q=Cowie%2C+J%2E%2C+and+Lehnert%2C+W%2E%2C+1996%2E+%22Information+Extraction%22%2C+Communications+of+the+ACM%2C+Vol%2E+39%2C+No%2E+1%2C+pp%2E+83%2D92%2E) 6. Evens, M., and Smith, R., 1978. "A Lexicon for Computer Question Answering System". American Journal of Computational Linguistics, Microfiches 81, pp. 16-24, and 83, pp. 1-98. [find](https://scholar.google.com/scholar?q=Evens%2C+M%2E%2C+and+Smith%2C+R%2E%2C+1978%2E+%22A+Lexicon+for+Computer+Question+Answering+System%22%2E+American+Journal+of+Computational+Linguistics%2C+Microfiches+81%2C+pp%2E+16%2D24%2C+and+83%2C+pp%2E+1%2D98%2E) 7. Evens, M., Vandendorpe, J., and Wang Y., 1985, "Lexical-Semantic Relations in Information Retrieval". In Humans and Machines. S. Williams, (ed.), Ablex, Norwood, NJ, pp.73-100. [find](https://scholar.google.com/scholar?q=Evens%2C+M%2E%2C+Vandendorpe%2C+J%2E%2C+and+Wang+Y%2E%2C+1985%2C+%22Lexical%2DSemantic+Relations+in+Information+Retrieval%22%2E+In+Humans+and+Machines%2E+S%2E+Williams%2C+%28ed%2E%29%2C+Ablex%2C+Norwood%2C+NJ%2C+pp%2E73%2D100%2E) 8. Hasnah, A., 1996. Full Text Processing and Retrieval: Weight Ranking, Text Structuring, and Passage Retrieval For Arabic Documents. Ph.D. Dissertation, Illinois Institute of Technology, Chicago, IL. [find](https://scholar.google.com/scholar?q=Hasnah%2C+A%2E%2C+1996%2E+Full+Text+Processing+and+Retrieval%3A+Weight+Ranking%2C+Text+Structuring%2C+and+Passage+Retrieval+For+Arabic+Documents%2E+Ph%2ED%2E+Dissertation%2C+Illinois+Institute+of+Technology%2C+Chicago%2C+IL%2E) 9. Kim, J-S., and Evens, M., 1995. "Extracting Personal Names from the Wall Street Journal", Proceedings of the 6 Midwest Artificial Intelligence and Cognitive Science Society Conference, Carbondale, IL, April 21-23, pp. 78-82. [find](https://scholar.google.com/scholar?q=Kim%2C+J%2DS%2E%2C+and+Evens%2C+M%2E%2C+1995%2E+%22Extracting+Personal+Names+from+the+Wall+Street+Journal%22%2C+Proceedings+of+the+6+Midwest+Artificial+Intelligence+and+Cognitive+Science+Society+Conference%2C+Carbondale%2C+IL%2C) 10. McCawley, J. 1986. "What Linguists Might Contribute to Dictionary Making If They Could Get Their Act Together". In P. Bjarkman and V. Raskin (eds.), The Real World Linguistics, Ablex, Norwood, N J, 1986. [find](https://scholar.google.com/scholar?q=McCawley%2C+J%2E+1986%2E+%22What+Linguists+Might+Contribute+to+Dictionary+Making+If+They+Could+Get+Their+Act+Together%22%2E+In+P%2E+Bjarkman+and+V%2E+Raskin+%28eds%2E%29%2C+The+Real+World+Linguistics%2C+Ablex%2C+Norwood%2C+N+J%2C+19) 11. Mikheev A., 1997. "Automatic Rulelnduction for Unknox~aa-Word Guessing". [find](https://scholar.google.com/scholar?q=Mikheev+A%2E%2C+1997%2E+%22Automatic+Rulelnduction+for+Unknox%7Eaa%2DWord+Guessing%22%2E) 12. Computational Linguistics, Voi.23, No.3, September 1997. pp. 405-423. [find](https://scholar.google.com/scholar?q=Computational+Linguistics%2C+Voi%2E23%2C+No%2E3%2C+September+1997%2E+pp%2E+405%2D423%2E) 13. Nutter, J. T., Fox, E., and Evens, M., 1990, "Building a Lexicon from Machine-Readable Dictionaries for Improved Information Retrieval", Literary and Linguistic Computing, Vol. 2, No. 5, pp.l-18. [↗](https://doi.org/10.1093/llc/5.2.129) 14. Paik, W., Liddy, E. D., Yu, E., and Mckenna, M., 1993. "Categorizing and Standardizing Proper Nouns for Efficient Information Retrieval", In B. Boguraev and J. Pustejovsky, eds, C o r p u s Processing for Lexical Acquisition, MIT Press, Cambridge, Mass, pp.44-54. [find](https://scholar.google.com/scholar?q=Paik%2C+W%2E%2C+Liddy%2C+E%2E+D%2E%2C+Yu%2C+E%2E%2C+and+Mckenna%2C+M%2E%2C+1993%2E+%22Categorizing+and+Standardizing+Proper+Nouns+for+Efficient+Information+Retrieval%22%2C+In+B%2E+Boguraev+and+J%2E+Pustejovsky%2C+eds%2C+C+o+r+p+u+s+Processing) 15. Rau, L. F., 1991. "Extracting Company Names from Text", Proceedings of the Seventh Conference on Artificial Intelligence Applications, Feb. 24-28, Miami Beach, Florida, pp.29-32. [find](https://scholar.google.com/scholar?q=Rau%2C+L%2E+F%2E%2C+1991%2E+%22Extracting+Company+Names+from+Text%22%2C+Proceedings+of+the+Seventh+Conference+on+Artificial+Intelligence+Applications%2C+Feb%2E+24%2D28%2C+Miami+Beach%2C+Florida%2C+pp%2E29%2D32%2E) 16. Wacholder, N., Ravin, Y., and Choi, M., 1997. "Disambiguation of Proper Names in Text", Proceedings of the Fifth Conference on Applied Natural Language Processing, Mar 31- Apr 3, Washington, DC, pp.202-208. [find](https://scholar.google.com/scholar?q=Wacholder%2C+N%2E%2C+Ravin%2C+Y%2E%2C+and+Choi%2C+M%2E%2C+1997%2E+%22Disambiguation+of+Proper+Names+in+Text%22%2C+Proceedings+of+the+Fifth+Conference+on+Applied+Natural+Language+Processing%2C+Mar+31%2D+Apr+3%2C+Washington%2C+DC%2C+pp%2E20) 17. Weischedel, R., Meteer, M., Schwartz, R., Ramshaw, L., and Palmucci, J., 1993. "Coping with Ambiguity and Unknown Words through Probabilistie M o d e l s " . Computational Linguistics, Vol. 19, No.2, pp.359-382. [find](https://scholar.google.com/scholar?q=Weischedel%2C+R%2E%2C+Meteer%2C+M%2E%2C+Schwartz%2C+R%2E%2C+Ramshaw%2C+L%2E%2C+and+Palmucci%2C+J%2E%2C+1993%2E+%22Coping+with+Ambiguity+and+Unknown+Words+through+Probabilistie+M+o+d+e+l+s+%22+%2E+Computational+Linguistics%2C+Vol%2E+19%2C+No%2E2%2C+) 18. Wolinski, F., Vichet, F., and Dillet, B., 1995. "Automatic Processing of Proper Names in Text". Proceedings of the 7 th Conference of the European Chapter of the Association for Computational Linguistics, Dublin, Ireland, pp. 23-30. [find](https://scholar.google.com/scholar?q=Wolinski%2C+F%2E%2C+Vichet%2C+F%2E%2C+and+Dillet%2C+B%2E%2C+1995%2E+%22Automatic+Processing+of+Proper+Names+in+Text%22%2E+Proceedings+of+the+7+th+Conference+of+the+European+Chapter+of+the+Association+for+Computational+Linguist) 19. Zhang, B.-T. and K i m , Y.-T., 1990. "Morphological Analysis and Synthesis by Automated Discovery and Acquisition of Linguistic Rules". Proceedings of the 13 th International Conference on Computational Linguistics (COLING-90), pp. 431-435. [find](https://scholar.google.com/scholar?q=Zhang%2C+B%2E%2DT%2E+and+K+i+m+%2C+Y%2E%2DT%2E%2C+1990%2E+%22Morphological+Analysis+and+Synthesis+by+Automated+Discovery+and+Acquisition+of+Linguistic+Rules%22%2E+Proceedings+of+the+13+th+International+Conference+on+Computatio) *Updated 1 November 2026*