Elamur Research⌕
☰
home / papers / 2022 / Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic

Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic

Paper · 2022 · Amany Fashwan and Sameh Alansary

Summary

The paper tackles the lack of morphological tools for Egyptian Arabic (EGY). Analyzers built for Modern Standard Arabic (MSA) handle dialects poorly, and existing EGY resources are either closed or normalized toward MSA spelling. The authors compiled a corpus of about 527,000 EGY words from social media, books and web articles written between 2011 and 2019. On this corpus they designed a POS tag-set that treats prefixes, stems and suffixes as separate tokens and assigns tags by both form and function. About 318,940 words were annotated in context. Each word carries a conventional EGY lemma and stem, an MSA lemma, a gloss, and gender, number and definiteness. From these annotations they automatically derived stem, prefix and suffix lexicons plus compatibility tables, which together drive a rule-based analyzer with an OOV fallback. On a blind 5,000-word sample, the correct analysis appeared among the candidates for 66.9% of words, compared with 82.1% for CALIMA. The gap mostly reflects the smaller lexicon at this in-progress stage. The work provides an openly accessible, dialect-faithful resource for EGY.

Key points

  • Corpus: about 527,000 EGY words, reported as roughly 82,700 tokens, drawn from multiple sources and genres. Six trained annotators produced about 318,940 context-annotated words.

  • Annotation features per word:

    • raw word and edited word
    • conventional EGY lemma (undiacritized for now) and conventional stem
    • MSA lemma, with "CMB" for combined origins and "LNW" for loanwords
    • person; gender (M/F); number (S/D/P/B, where B is broken plural); definiteness (D/I/E, where E is an EDAFAH governor)
    • gloss and POS tags

  • Extracted lexicons: 39K stems, covering about 12,100 EGY lemmas and 18,400 MSA lemmas, plus 324 complex prefixes and 661 complex suffixes. CALIMA, for comparison, has 100K stems, 36K lemmas, 2,421 prefixes and 1,179 suffixes.

  • The analyzer works in four steps:

    1. preprocessing and parsing the lexicons
    2. proposing segmentations and checking them against the compatibility tables
    3. handling OOV words
    4. writing the results as XML

  • Blind test results:

    Correct analysis among candidatesCandidates, none correctNo analysis
    This system66.9%10.3%22.8%
    CALIMA82.1%9.6%8.3%

Interesting ideas

  • I1. Compatibility tables are read off annotated data, and any prefix–stem–suffix category combination never seen together is treated as invalid, which keeps the analyzer from overgenerating without hand-written rules.
  • I2. Only one conventional stem is stored, and predictable spelling variants are generated from it at lookup time; variants that cannot be predicted are listed explicitly.
  • I3. OOV words get a layered fallback. The analyzer first tries splitting off commonly fused particles and keeps both the raw and normalized forms; failing that, it guesses affixes and matches the stem pattern, returning a category but deliberately no lemma or gloss.
  • I4. Coverage is measured as candidate recall and split into three buckets: correct analysis present, only wrong analyses, and nothing returned. This separates lexicon gaps from wrong analyses.
  • I5. Each dialect lemma is linked to a standard-language lemma, and explicit markers cover cases with no counterpart, such as combined expressions and loanwords.

For Mova

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

  • I1 (tokens): the en morphology could learn allowed stem/affix category pairings from treebank data and reject unattested analyses before tagging.
  • I2 (tokens): keep a single canonical lexicon entry per lemma and expand regular spelling variants (British/American, hyphenation, informal spellings) on the fly, while still logging irregular ones.
  • I3 (tokens): unknown words could carry an explicit "category guessed, lemma unknown" status, so later stages can tell how much to trust them.
  • I4 (learn): evaluate the morphology and candidate generators with the same three-way breakdown, so missing coverage and bad candidates show up as separate failure signals.
  • I5 (world): when mapping lemmas to WordNet/Wikidata, mark "no counterpart" and "multiword origin" explicitly instead of forcing a link, so the ontology layer stays explainable.

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

🎓Alexandria UniversityAlexandria · Egypt39 works · 287 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 2Research subjects and languages the work is about.Semitic languages · 2,908 worksMorphology · 405 works

Cite

Cite as Amany Fashwan and Sameh Alansary. 2022. Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic. Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.wanlp-1.14

@inproceedings{fashwan2022developing,
  title = {{Developing a Tag-Set and Extracting the Morphological Lexicons to Build a Morphological Analyzer for Egyptian Arabic}},
  author = {Amany Fashwan and Sameh Alansary},
  booktitle = {Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)},
  year = {2022},
  doi = {10.18653/v1/2022.wanlp-1.14},
  url = {https://doi.org/10.18653/v1/2022.wanlp-1.14}
}

References

31 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abo Bakr, H. A., Shaalan, K., & Ziedan, I. (2008). A hybrid approach for converting written Egyptian colloquial dialect into diacritized Arabic. In The 6th international conference on informatics and systems, infos2008. Cairo. Retrieved 7 27, 2018, from https://www.researchgate.net/profile/Khaled_Shaa lan/publication/206006074_A_Hybrid_Approach_ for_Converting_Written_Egyptian_Colloquial_Di alect_into_Diacritized_Arabic/links/0912f505a298 ee3308000000.pdf Al Ameri, S. S., & Shoufan, A. (2021). Building Lexical Resources for Dialectical Arabic. In Natural Language Processing for Global and Local Business (pp. 332-364). IGI Global. ↗
  2. Al-Dahah, A. (1989). A Dictionary of Arabic Grammer in Charts and Tables " لوادج يف ةيبرعلا ةغللا دعاوق مجعم تاحولو ". Beirut, Lebanon: Librairie du Liban publisher. find
  3. Alqrainy, S. (2008). A morphological-syntactical analysis approach for Arabic textual tagging. Leicester, UK: De Montfort University. Retrieved 11 8, 2021 find
  4. Al-Sabbagh, R., & Girju, R. (2010). Mining the Web for the Induction of a Dialectical Arabic Lexicon. In LREC. Retrieved 6 23, 2019, from https://www.researchgate.net/profile/Rania_Al-Sabbagh/publication/220746429_Mining_the_We b_for_the_Induction_of_a_Dialectical_Arabic_Le xicon/links/02e7e51597e45d9c5d000000.pdf Al-Sabbagh, R., & Girju, R. (2012). YADAC: Yet another Dialectal Arabic Corpus. In LREC, (pp. 2882-2889). Retrieved 6 23, 2019, from https://pdfs.semanticscholar.org/67ad/6967eb602c 7416e8aaa138bb4c45a23b4e07.pdf Atwell, E. (2008). Development of tag sets part-of-speech tagging. In A. Ludeling, & M. Kyto (Eds.), Handbook, Corpus Linguistics: An International (Vol. 1, pp. 501 - 526). Walter de Gruyter. Retrieved 7 5, 2019, from https://eprints.whiterose.ac.uk/81781/1/Developm entTagSetPOSTagging.pdf Bouamor, H, Habash, N., Salameh, M., Zaghouani, W., Rambow, O., Abdulrahim, D., Obeid, O., Khalifa, S., Eryani, F., Erdmann, A., & Oflazer, K. (2018). The MADAR Arabic Dialect Corpus and Lexicon. In Proceedings of the 11th International Conference on Language Resources and Evaluation. Retrieved 8 7, 2018, from http://www.lrec-conf.org/proceedings/lrec2018/pdf/351.pdf ↗
  5. Buckwalter, T. (2004). Buckwalter Arabic Morphological Analyzer Version 2.0. Linguistic Data Consortium, University of Pennsylvania, 2004. LDC Catalog No.: LDC2004L02. Retrieved 11 20, 2019, from https://catalog.ldc.upenn.edu/LDC2004L02 ↗
  6. Darwish, K., Mubarak, H., Abdelali, A., Eldesouki, M., Samih, Y., Alharbi, R., Attia, M., Magdy, W., & Kallmeyer, L. (2018). Multi-Dialect Arabic POS Tagging: A CRF Approach. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC. Retrieved 6 19, 2019, from https://www.aclweb.org/anthology/L18-1015 ↗
  7. Diab, M., Al-Badrashiny, M., Aminian, M., Attia, M., Dasigi, P., Elfardy, H., Eskander, E., Nizar, H., Hawwari, A., & Salloum, W. (2014). Tharwa: A Large Scale Dialectal Arabic-Standard Arabic-English Lexicon. In LREC, (pp. 3782-3789). Retrieved 7 28, 2018, from https://www.researchgate.net/profile/Mohammed_ Attia2/publication/305489865_Tharwa_A_Large_ Scale_Dialectal_Arabic-Standard_Arabic-English_Lexicon/links/582f14bb08ae138f1c034db 8.pdf Eldesouki, M., Samih, Y., Abdelali, A., Attia, M., Mubarak, H., Darwish, K., & Laura, K. (2017). Arabic multi-dialect segmentation: bi-LSTM-CRF vs. SVM. Retrieved 9 1, 2022, from https://arxiv.org/pdf/1708.05891.pdf ↗
  8. Eskander, R., Habash, N., & Rambow, O. (2013). Automatic Extraction of Morphological Lexicons from Morphologically Annotated Corpora. In Proceedings of the 2013 conference on empirical methods in natural language processing, (pp. 1032-1043). Retrieved 7 4, 2019, from https://www.aclweb.org/anthology/D13-1105 from https://aclanthology.org/2022.sigmorphon-1.10.pdf ↗
  9. Fashwan, A., & Alansary, S. (2021). A Morphologically Annotated Corpus and a Morphological Analyzer for Egyptian Arabic. Procedia Computer Science. 189, pp. 203-210. find
  10. Habash, N., Roth, R., Rambow, O., Eskander, R., & Tomeh, N. (2013). Morphological analysis and disambiguation for dialectal Arabic. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (pp. 426-432). Retrieved 7 3, 2019, from https://www.aclweb.org/anthology/N13-1044 ↗
  11. Habash, N. (2010). Introduction to Arabic natural language processing. Synthesis Lectures on Human Language Technologies Journal, Vol. 3, pp. 1-187. ↗
  12. Habash, N., & Rambow, O. (2005). Arabic Tokenization, Part-of-Speech Tagging and Morphological Disambiguation in One Fell Swoop. In Proceedings of the 43rd annual meeting of the association for computational linguistics (ACL’05), (pp. 573-580). Retrieved 7 4, 2019, from https://www.aclweb.org/anthology/P05-1071 ↗
  13. Habash, N., & Rambow, O. (2006). MAGEAD: A Morphological Analyzer and Generator for the Arabic Dialects. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, (pp. 681-688). Retrieved 6 24, 2019, from https://www.aclweb.org/anthology/P06-1086 ↗
  14. Habash, N., Diab, M., & Rambow, O. (2012). Conventional Orthography for Dialectal Arabic. In LREC, (pp. 711-718). Retrieved 6 19, 2019, from http://www.lrec-conf.org/proceedings/lrec2012/pdf/579_Paper.pdf ↗
  15. Habash, N., Eryani, F., Khalifa, S., Rambow, O., Abdulrahim, D., Erdmann, A., . . . Saddiki, H. (2018). Unified guidelines and resources for Arabic dialect orthography., (pp. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)). Retrieved 6 19, 2019, from https://www.aclweb.org/anthology/L18-1574 ↗
  16. Habash, N., Eskander, R., & Hawwari, A. (2012). A morphological Analyzer for Egyptian Arabic. In Proceedings of the twelfth meeting of the special interest group on computational morphology and phonology (pp. 1-9). Association for Computational Linguistics. Retrieved 7 29, 2018, from https://aclanthology.org/W12-2301.pdf ↗
  17. Habash, N., Marzouk, R., Khairallah, C., & Khalifa, S. (2022). Morphotactic Modeling in an Open-source Multi-dialectal Arabic Morphological Analyzer and Generator. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, (pp. 92-102). Retrieved 7 1, 2022, Harrat, S., Meftouh, K., & Smaïli, K. (2017). Machine translation for Arabic dialects (survey). Information Processing and Management. Retrieved 7 28, 2018, from https://www.researchgate.net/profile/Kamel_Smail i/publication/319423437_Machine_translation_for _Arabic_dialects_survey/links/5a0a32f0a6fdcc273 6dea63b/Machine-translation-for-Arabic-dialects-survey.pdf Chang, J. Z., & Chang, J. S. (2012). Word root finder: a morphological segmentor based on CRF. Proceedings of COLING 2012: Demonstration Papers. Retrieved from 2012: https://aclanthology.org/C12-3007.pdf ↗
  18. Khalifa, S., Habash, N., Eryani, F., Obeid, O., Abdulrahim, D., & Al Kaabi, M. (2018). A morphologically annotated corpus of Emirati Arabic. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018). Retrieved 5 29, 2021, from https://aclanthology.org/L18-1607.pdf ↗
  19. Khoja, S. (2003). APT: An automatic arabic part-of-speech tagger. Doctoral dissertation. Lancaster University. Retrieved 11 8, 2021 find
  20. Khoja, S., Garside, R., & Knowles, G. (2001). An Arabic tagset for the morphosyntactic tagging of Arabic. Doctoral dissertation, 13, . Lancaster University (UK). Retrieved 8 11, 2021 find
  21. Kilany, H., Gadalla, H., Arram, H., Yacoub, A., El-Habashi, A., & McLemore, C. (2002). Egyptian Colloquial Arabic Lexicon. LDC catalog number LDC99L22. Retrieved 8 5, 2019, from https://catalog.ldc.upenn.edu/LDC99L22 ↗
  22. Maamouri, M., & Bies, A. (2004). Developing an Arabic treebank: Methods, guidelines, procedures, and tools. In Proceedings of the Workshop on Computational Approaches to Arabic Script-based languages, (pp. 2-9). Retrieved 11 8, 2021, from https://aclanthology.org/W04-1602.pdf ↗
  23. Maamouri, M., Bies, A., Buckwalter, T., Diab, M. T., Habash, N., Rambow, O., & Tabessi, D. (2006). Developing and Using a Pilot Dialectal Arabic Treebank. In LREC, (pp. 443-448). Retrieved 8 4, 2018, from https://www.ldc.upenn.edu/sites/www.ldc.upenn.e du/files/lrec2006-developing-using-dialectal-arabic-treebank.pdf Maamouri, M., Bies, A., Krouna, S., Gaddeche, F., & Bouziri, B. . (2009). Penn Arabic treebank guidelines. Linguistic Data Consortium. ↗
  24. Maamouri, M., Bies, A., Kulick, S., Ciul, M., Habash, N., & Eskander, R. (2014). Developing an Egyptian Arabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development. LREC, (pp. 2348-2354). Retrieved 6 1, 2021, from http://www.lrec-conf.org/proceedings/lrec2014/pdf/1145_Paper.pd f Maamouri, M., Krouna, S., Tabessi, D., Hamrouni, N., & Habash, N. (2012). Arabic Treebanking Egyptian Arabic (ARZ) Morphological (ARZGM) Version 1.21 (With Permession). Retrieved 08 21, 2022, from https://www.researchgate.net/publication/3313154 55_Egyptian_Arabic_Morphological_Annotation_ Guidelines/stats Mohamed, E., Mohit, B., & Oflazer, K. (2012). Annotating and Learning Morphological Segmentation of Egyptian Colloquial Arabic. In LREC, (pp. 873-877). Retrieved 7 4, 2019, from http://nlp.qatar.cmu.edu/papers/465_Paper.pdf ↗
  25. Parkinson, D. B. (1981). VSO to SVO in Modern Standard Arabic: A study in diglossia syntax. In al-'Arabiyya (Vol. 14, pp. 24-37). Georgetown University Press. Retrieved 5 15, 2021 find
  26. Salloum, W., & Habash, N. (2014). ADAM: Analyzer for Dialectal Arabic Morphology. Journal of King Saud University-Computer and Information Sciences, 26(4), 372-378. Retrieved 7 30, 2018, from https://www.sciencedirect.com/science/article/pii/ S1319157814000342 ↗
  27. Samih, Y., & Kallmeyer, L. (2017). Dialectal Arabic Processing Using Deep Learning. Doctoral dissertation, Ph. D. thesis, Heinrich-Heine-Universität Düsseldorf, Düsseldorf. Germany. Retrieved 8 5, 2018, from https://docserv.uniduesseldorf.de/servlets/DerivateServlet/Derivate-47492/Dissertation_younes_samih.pdf ↗
  28. Sawalha, M. S. (2011). Open-source resources and standards for Arabic word structure analysis: Fine grained morphological analysis of Arabic text corpora. University of Leeds. find
  29. Shaalan, K., Bakr, H., & Ziedan, I. (2007). Transferring egyptian colloquial dialect into modern standard arabic. In International Conference on Recent Advances in Natural Language Processing (RANLP–2007), (pp. 525-529). Borovets, Bulgaria. Retrieved 6 10, 2019, from http://www.linguisticsnetwork.com/wp-content/uploads/Transferring-Egyptian-Colloquial-Dialect-into-Modern-Standard-Arabic-2.compressed.pdf ↗
  30. Zalmout, N., Erdmann, A., & Habash, N. (2018). Noise-Robust Morphological Disambiguation for Dialectal Arabic. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (Long Papers), Volume 1 , pp. 953-964. Retrieved 7 4, 2019, from https://www.aclweb.org/anthology/N18-1087 ↗
  31. Salloum, W., & Habash, N. (2011). Dialectal to standard Arabic paraphrasing to improve Arabic-English statistical machine translation. In Proceedings of the first workshop on algorithms and resources for modelling of dialects and language varieties (pp. 10-21). Association for Computational Linguistics. Retrieved 7 26, 2018, from http://delivery.acm.org/10.1145/2150000/2140535/p10-salloum.pdf?ip=196.204.161.40&id=2140535&ac c=OPEN&key=4D4702B0C3E38B35%2E4D4702 B0C3E38B35%2E4D4702B0C3E38B35%2E6D2 18144511F3437&__acm__=1560078805_b75acb 510a9652c29cada891c1ec3bd2 A Nouns Noun Sub Classes Noun ‘ مس لاا ’ /ɑl-ism/ (NOU) Description and Example It is the common noun that refers to entities and concepts that have a more general reference than sub-tags. .هيب اوبحر ني سردم لا لك و موي لوأ يف ه ت مام عم ه ت سردم حار دلو لاو wil-wælæd rɑːħ mædræstu mæʢæ mɑːmtu fiː ʡæwwil jʊ m wi-kull ɑl-mudarrisiːn ræħæbuː biːh Proper Noun ‘ملعلا مسا’ /ism ɑl-ʢælæm/ (NOU_PRP) It is a noun that has a unique referential meaning in a context that is mutually exclusive with other entities. It refers to names of people, geographical entities, months, and acronyms. . ة يردنكسإ يف اهتقو انكو ةدك سرام رهش لوأ هد ملكلا يلاق يللا وه دمحم mæħæmmæd huwwæ illiː ʡɑːlliː ɑl-kælɑːm dæh fiː ʡæwwil ʃæhr mɑːris kidæ wi-kunnɑː wæʡtæhæ fiː ʡiskindirijjæ Numeral Noun ‘ددعلا مسا’ /ism ɑl-ʢædæd/ It is a noun that indicates the quantity and order of countable nouns by transferring the numbers into the correct form of Arabic words. . رفص / دحاو كلامزلا بلغ يلهلأا (NOU_NUM) ɑl-ʡæhliː ɤælæb ɑz-zæmɑːlik wɑːħid/ʂifr Adjective ‘ةفصلا’ /ɑʂ-ʂifæ/ (ADJ) It is a noun that describes or clarifies the meaning of the immediately preceding noun. .اهتمام ملك عمست ة رطاش لا تنبلا ɑl-bint ɑʃ-ʃɑːṭræ tismæʢ kælɑːm mɑːmithɑː Numeral Adjective ‘ ةفصلا It is an adjective that indicates the quantity and order of countable nouns by ددعلا’ /ɑʂ-ʂifæ ɑl-ʢædæd/ transferring the numbers into the correct form of Arabic words. . رشع ة يداحلا ةياكحلا (ADJ_NUM) ɑl-ħikɑːjæh ɑl-ħɑːdijætæ ʢæʃær Nominal Adjective ‘ ةفصلا It is a noun that describes or clarifies the meaning of a noun, but it appears as ةيمسلاا’ /ɑʂ-ʂifæ ɑl-ismijjæ/ (ADJ_NOM) the main predicate of a nominal phrase in the sentence. .ادبأ اهقلخأ يف تن ب تفش ام يرمعو ة ليمج يقيقح تناك kɑːnit ħæʡiːʡiː gæmiːlæ wi-ʢumriː mɑː ʃuft bint fiː ʡæ x lɑːʡhɑː Superlative Adjective ‘ ةفص ليضفت’ /ʂifæt tæfd iːl/ It is a noun that is used for the comparative and superlative when comparing persons or things. It describes the immediately preceding noun. .تكاس تنإو ملكلا عمست كنإ اهل معت يللا ىلح لأا ةجاحلا (ADJ_SUP) ɑl-ħɑːgæ ɑl-ʡæħlæː illiː tiʢmilhɑː ʡinnak tismæʢ ɑl-kælɑːm wi-ʡintæ sɑːkit Superlative Noun ‘ليضفت مسا’ It is a noun that is used for the comparative and superlative when comparing /ism tæfd iːl/ persons or things, but it appears as the main predicate of a nominal phrase in (NOU_SUP) the sentence. .يتايح يف يلتلصح ةجاح لمجأ تناك يد اللهو wɑl-læhiː diː kɑːnt ʡægmæl ħɑːgæ ħæʂælitliː fiː ħæjɑːtiː Adverb of Place ‘ناكملا مسا’ /ism ɑl-mækɑːn/ (ADV_PLC) It is a noun that indicates where the action of a verb is or was carried out. .مويلا لوط تيبلا ة وج دعق ʡæʢæd juwwæ ɑl-beɪt ṭuːl ɑl-jʊ m Noun Sub Classes Description and Example Adverb of Time ‘ نامزلا م سا ’ It is a noun that indicates when the action of a verb happened. It expresses a /ism ɑz-zæmɑːn/ (ADV_TIM) point in time, and it can also indicates how long something lasted or lasts. .لأ لاو ة ركب ينات هفوشأ ردقح فراع شمو حرابمإ هفياش هسل اللهو wɑl-læhiː lissæ ʃɑːjfuh ʡimbɑːriħ wi-miʃ ʢɑːrif ħæ-ʡdær ʡæʃuːfuh tɑːniː bukræ wællæ læʡ Adverb of both Time and It is a noun that could be used as an adverb of time or place according to its Place ‘ناكمو نامز مسا’ /ism context. mækɑːn wɑ-zæmɑːn/ (ADV_TPL) .تيبلل تاجاح بيجي تكرام ربوسلا د نع حيار ناك kɑːn rɑːjiħ ʢænd ɑs-suːbær mɑːrkit jigiːb ħɑːgɑːt lil-beɪt .صلاخ بلقتا عضولا يد ةظحللا دنع و wi-ʢænd ɑl-læħzˤæ diː ɑl-wæd ʢ itʡælæb x ɑːliʂ Adverb of Manner ‘لاح’ It is a noun that describes the circumstances under which an action takes place. /ħɑːl/ . ة ناحرس تدعق بعتلا رتك نمو يوق ة نابع ت ةياج تنك kunt gɑːjjæ tæʢbɑːnæ ʡæwiː wi-min kutr ɑt-tæʢæb ʡæʢædt sarħɑːnæ (ADV_MNN) Adverb of Degree ‘ فرظ It is a noun that indicates the intensity of a verb, adjective, or another adverb. لاحلا ةجرد وأ لاح لا ’ /zˤærf ɑl-It is not found in MSA, but it is added to EGY in the current tag-set schema. ħɑːl ʡæw dærægæt ɑl-ħɑːl/ (ADV_DGR) . ا دج كبحب يقيقح انأ ʡænɑː ħæʡiːʡiː bæħibbæk jiddæn سب ةدحاو ةملك كنم عمسأ يسفن ناك kɑːn nifsiː ʡæsmæʢ minnæk kilmæ wɑːħæ bæs Pronoun ‘ريمضلا’ /ɑd - d æmiːr/ It is a word that acts as the subject of a sentence instead of a noun. The pronouns in this category are the disconnected pronouns. (PRN) The pronouns in this category are: انأ ʡænɑː, انحإ ʡiħnɑː, تنإ ʡintæ, يتنإ ʡintiː, وه huwwæ, يه hijjæ, امه hummɑː, and وتنإ ʡintuː Relative Pronoun ‘ مسلا ا لوصوملا’ /ɑl-ism ɑl-mæwʂ It is a noun that introduces relative clauses. It connects two sentences to give a full meaning. uːl/ (PRN_DEM) .حص ناك هانلوق يللا ملكلا ɑl-kælɑːm illiː ʡulnɑːh kɑːn ʂæħħ Demonstrative Pronoun ‘ مسا ةراشلإا’ /ism ɑl- ʡiʃɑːræ/ It is a noun that is used for proximal or distal reference. It is indicated by a tangible sign a person, an animal, a thing, or a place. (PRN_REL) .صلاخ مهاسنت لود سانلاو ينات هعمسأ ةزياع شم هد هتلوق يللا illiː ʡultuː dæh miʃ ʢæjzæ ʡæsmæʢuː tɑːniː win-nɑːs dʊ l tinsɑːhum x ɑːliʂ Interrogative Pronouns ‘ مسا It is a noun that introduces a question about something or an action. ماهفتسلاا’ /ism ɑl- istifhɑːm/ (PRN_INT) ؟لصأ لود سانلا نيمو ىتمإو يازإ لصح هد ةفراع شم انأ ʡænɑː miʃ ʢɑːrfæ dæh ħæʂæl ʡizzɑːj wi-ʡimtæː wi-miːn ɑn-nɑːs dʊ l ʡæʂlæn B Verbs Verb Sub Classes Active Verb ‘ ينبملا لعفلا مولعملل’ /ɑl-fiʢl ɑl-mæbniː lil-mæʢluːm/ (VER_ACT:<tense>) ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/fashwan-2022-developing-tag-set-extracting-morphological/