[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/aclbulk-2008-gabbard-construct-state-modification-arabic-treebank/) [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/) / Construct State Modification in the Arabic Treebank # Construct State Modification in the Arabic Treebank **Authors:** [Ryan Gabbard](https://md.mova.elamur.ai/free/en/docs/papers/authors/ryan-gabbard/); [Seth Kulick](https://md.mova.elamur.ai/free/en/docs/papers/authors/seth-kulick/) · **Year:** 2008 · **Venue:** Proceedings of ACL-08: HLT, Short Papers **Link:** [aclanthology.org/P08-2053](https://aclanthology.org/P08-2053/) · library `aclbulk-2008-gabbard-construct-state-modification-arabic-treebank` · **Licence:** [CC BY-NC-SA 3.0](https://creativecommons.org/licenses/by-nc-sa/3.0/) (ACL Anthology, before 2016) — summary only [**4** citations](https://openalex.org/works?filter=cites:W2111925493) openalex-snapshot · 2026-10-14[**2** citations in our library](https://md.mova.elamur.ai/free/en/docs/papers/cited-by/aclbulk-2008-gabbard-construct-state-modification-arabic-treebank/) of the 140673 papers whose bibliographies we read[Proceedings of ACL-08: HLT, Short Papers](https://aclanthology.org/volumes/P08-2/)[licence](https://creativecommons.org/licenses/by-nc-sa/3.0/) - [Publisher's page](https://aclanthology.org/P08-2053/) - [PDF](https://aclanthology.org/P08-2053.pdf) - [DOI 10.3115/1557690.1557750](https://doi.org/10.3115/1557690.1557750) - [OpenAlex](https://openalex.org/W2111925493) **Authors (2)** 1. [Ryan Gabbard](https://openalex.org/A5102936432) [ORCID](https://orcid.org/0000-0002-2122-9678) · [Semantic Scholar](https://www.semanticscholar.org/author/50543673) · h 8 · 296 citations · 17 works 2. [Seth Kulick](https://openalex.org/A5090150146) [ORCID](https://orcid.org/0000-0002-1376-4902) · [Semantic Scholar](https://www.semanticscholar.org/author/2695965) · h 15 · 1114 citations · 139 works Citations and author metrics from openalex-snapshot (2026-10-14); authors with the same name are not always told apart. ## What it is about The Arabic Treebank (ATB) marks a construct-state (iDafa) noun phrase as a NOUN with an NP complement, and the NP can nest. Modifiers, especially prepositional phrases, can then attach at any level of such a chain. Earlier work had blamed this for weak PP attachment on the ATB, because the English "base NP" rule that controls PP attachment does not hold. The authors extract 9,472 iDafas from about 100K words of ATB3 (ANNAHAR); 3,877 of them carry modifiers, most with exactly one (72%), and almost all are of depth three or less. A maximum-entropy model attaches each modifier to a level, with the constraint that later attachments are never deeper than earlier ones, and a dynamic program finds the best joint assignment. The best feature set (the tag of the modifier plus a lexical pair of modifier head and modified noun) reaches 80% accuracy on the dev-test split, against 39.7% for the depth-only baseline. ## Ideas - I1. Store a construct chain as one unit with numbered levels (0 = top, 1 = below, and so on), and let each modifier attach to a level rather than to "the nearest NP". In the tree reader (`world`), a PP after the last noun of a chain should be recorded as attached to the chain, with its level, instead of to the last noun alone. - I2. A two-feature attachment classifier for the Hebrew construct chain (smichut): the category of the modifier plus the pair (chain head, modifier head), with the left-to-right depth constraint. It is small, rule-like and can be written as a table, so it is a good first test once `treebanks/hbo` trees are available. - I3. Keep the paper's 39.7% depth-only baseline as a negative control: a rule that always attaches to the most common level should score far below any feature model. A result near 40% means the test is not measuring anything. ## For Mova I1 goes into the chain handling of [Syntax: the clause and the sentence](https://md.mova.elamur.ai/free/en/docs/languages/hbo/08-syntax/) and [7. Syntax](https://md.mova.elamur.ai/free/en/docs/languages/he/07-syntax/) (the smichut and the genitive chain), and into the frame builder of `world`. I2 is a candidate model for [The Noun, the Adjective and the Numeral](https://md.mova.elamur.ai/free/en/docs/languages/hbo/04-noun/) once the MACULA-derived trees exist (`tools/macula`). I3 is a test to add to the same run. Topics: [Treebanks](https://md.mova.elamur.ai/free/en/docs/papers/topics/treebanks/) ## Cite The paper itself, not this card. BibTeX from the library's record of the work. [DOI 10.3115/1557690.1557750](https://doi.org/10.3115/1557690.1557750) ``` @inproceedings{gabbard2008construct, title = {{Construct State Modification in the Arabic Treebank}}, author = {Gabbard, Ryan and Kulick, Seth}, booktitle = {Proceedings of ACL-08: HLT, Short Papers}, year = {2008}, doi = {10.3115/1557690.1557750}, url = {https://doi.org/10.3115/1557690.1557750} } ``` - [← previous ElixirFM – Implementation of Functional Arabic Morphology](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2007-smrz-elixirfm-implementation-functional-arabic-morphology/) - [next → Arabic Morphological Tagging, Diacritization, and Lemmatization Using Lexeme Models and Feature Ranking](https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2008-roth-arabic-morphological-tagging-diacritization-lemmatization/) - [↑ back to Semitic languages](https://md.mova.elamur.ai/free/en/docs/papers/sem/) ## References 9 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. ATB. 2008. Arabic Treebank Morphological and Syntactic guidelines. [http://projects.ldc.upenn.edu/ArabicTreebank](http://projects.ldc.upenn.edu/ArabicTreebank). [↗](http://projects.ldc.upenn.edu/ArabicTreebank) 2. Ann Bies, Mark Ferguson, Karen Karz, and Robert Mac-Intyre. 1995. Bracketing guidelines for Treebank II-style Penn Treebank project. Technical report, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Ann+Bies%2C+Mark+Ferguson%2C+Karen+Karz%2C+and+Robert+Mac%2DIntyre%2E+1995%2E+Bracketing+guidelines+for+Treebank+II%2Dstyle+Penn+Treebank+project%2E+Technical+report%2C+University+of+Pennsylvania%2E) 3. Daniel M. Bikel. 2004. Intricacies of Collins’ parsing model. Computational Linguistics, 30(4). [↗](https://doi.org/10.1162/0891201042544929) 4. Tim Buckwalter. 2004. Arabic morphological analyzer version 2.0. LDC2004L02. Linguistic Data Consortium. [find](https://scholar.google.com/scholar?q=Tim+Buckwalter%2E+2004%2E+Arabic+morphological+analyzer+version+2%2E0%2E+LDC2004L02%2E+Linguistic+Data+Consortium%2E) 5. Michael Collins. 1999. Head-Driven Statistical Models for Natural Language Parsing. Ph.D. thesis, Department of Computer and Information Sciences, University of Pennsylvania. [find](https://scholar.google.com/scholar?q=Michael+Collins%2E+1999%2E+Head%2DDriven+Statistical+Models+for+Natural+Language+Parsing%2E+Ph%2ED%2E+thesis%2C+Department+of+Computer+and+Information+Sciences%2C+University+of+Pennsylvania%2E) [our card](https://md.mova.elamur.ai/free/en/docs/papers/cl-2003-collins-head-driven-statistical-models-natural/) 6. Mona Diab. 2007. Improved Arabic base phrase chunking with a new enriched pos tag set. In Proceedings of the 2007 Workshop on Computational Approaches to Semitic Languages. [find](https://scholar.google.com/scholar?q=Mona+Diab%2E+2007%2E+Improved+Arabic+base+phrase+chunking+with+a+new+enriched+pos+tag+set%2E+In+Proceedings+of+the+2007+Workshop+on+Computational+Approaches+to+Semitic+Languages%2E) 7. Seth Kulick, Ryan Gabbard, and Mitchell Marcus. 2006. Parsing the Arabic Treebank: Analysis and improvements. In Proceedings of TLT 2006. Treebanks and Linguistic Theories. [find](https://scholar.google.com/scholar?q=Seth+Kulick%2C+Ryan+Gabbard%2C+and+Mitchell+Marcus%2E+2006%2E+Parsing+the+Arabic+Treebank%3A+Analysis+and+improvements%2E+In+Proceedings+of+TLT+2006%2E+Treebanks+and+Linguistic+Theories%2E) 8. Mohamed Maamouri, Ann Bies, Seth Kulick, Fatma Gadeche, and Wigdan Mekki. 2007. Arabic treebank 3(a) - v2.6. LDC2007E65. Linguistic Data Consortium. [find](https://scholar.google.com/scholar?q=Mohamed+Maamouri%2C+Ann+Bies%2C+Seth+Kulick%2C+Fatma+Gadeche%2C+and+Wigdan+Mekki%2E+2007%2E+Arabic+treebank+3%28a%29+%2D+v2%2E6%2E+LDC2007E65%2E+Linguistic+Data+Consortium%2E) 9. Karin C. Ryding. 2005. A Reference Grammar of Modern Standard Arabic. Cambridge University Press. [↗](https://doi.org/10.1017/cbo9780511486975)