Improving Arabic Dependency Parsing with Form-based and Functional Morphological Features

What it is about

The authors ask which morphological features help a transition-based parser (MaltParser, eager algorithm, SVM classifiers) on Modern Standard Arabic. The data are the CATiB dependency trees converted from Penn Arabic Treebank part 3, with features predicted by MADA rather than taken from gold. Nine inflectional features and three lexical ones (undiacritized lemma, root, pattern) are added one at a time, greedily, and in combination. Definiteness, person/number/gender and the undiacritized lemma help most; adding all nine features together hurts, because low-accuracy predictions (case, 86.3%) dominate. Functional gender and number (the "broken plurals" case) and the rationality feature beat surface features: the best CORE 12 setup reaches 80.53% LAS against a 78.68% baseline, and the best setup overall, with the CATiB-EX tagset, reaches 80.83% LAS.

Ideas

• I1. Gate each predicted feature by its own measured accuracy before it enters the parser: keep a feature only if its prediction accuracy clears a threshold, because the all-features setup failed for that reason. For Hebrew this is a check inside tools/hbo before gparse receives any predicted tag.
• I2. Measure the undiacritized lemma as a parser feature: the paper's strongest lexical feature is the lemma without vowels, which is exactly what unpointed Hebrew input offers. Compare gparse on tools/hbo unpointed output with and without a consonantal-lemma feature, using macula dict as the lemma source.
• I3. Break the error count down by attachment type (subject, object, idafa, nominal modifier, prepositional) and check that agreement-bound relations improve more than the others. Use this as a diagnostic report for gparse runs on treebanks/hbo/ptnk.

For Mova

I1 belongs in tools/hbo (the feature gate before gparse). I2 is a test for the unpointed mode of tools/hbo, with macula dict as the lemma source. I3 is a report for gparse on treebanks/hbo/ptnk and macula compare. The paper's Arabic agreement facts are not transferred into The Noun, the Adjective and the Numeral without first checking them against the Hebrew treebank.

Topics: Dependency parsing · Treebanks

Cite

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

@inproceedings{marton2011improving,
  title = {{Improving Arabic Dependency Parsing with Form-based and Functional Morphological Features}},
  author = {Marton, Yuval and Habash, Nizar and Rambow, Owen},
  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  year = {2011},
  url = {https://aclanthology.org/P11-1159/}
}

References

27 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Sarah Alkuhlani and Nizar Habash. 2011. A corpus for modeling morpho-syntactic agreement in Arabic: gender, number and rationality. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL), Portland, Oregon, USA. find our card
2. Sabine Buchholz and Erwin Marsi. 2006. CoNLL-X shared task on multilingual dependency parsing. In Proceedings of Computational Natural Language Learning (CoNLL), pages 149–164. find our card
3. Timothy A. Buckwalter. 2004. Buckwalter Arabic Morphological Analyzer Version 2.0. Linguistic Data Consortium, University of Pennsylvania, 2002. LDC Cat alog No.: LDC2004L02, ISBN 1-58563-324-0. find
4. Michael Collins, Jan Hajic, Lance Ramshaw, and Christoph Tillmann. 1999. A statistical parser for czech. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL), College Park, Maryland, USA, June. find
5. Brooke Cowan and Michael Collins. 2005. Morphology and reranking for the statistical parsing of spanish. In Proceedings of Human Language Technology (HLT) and the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 795–802. find
6. Ali Dada. 2007. Implementation of Arabic numerals and their syntax in GF. In Proceedings of the Workshop on Computational Approaches to Semitic Languages, pages 9–16, Prague, Czech Republic. find
7. Mona Diab. 2007. Towards an optimal pos tag set for modern standard arabic processing. In Proceedings of Recent Advances in Natural Language Processing (RANLP), Borovets, Bulgaria. find
8. Gülsen Eryigit, Joakim Nivre, and Kemal Oflazer. 2008. Dependency parsing of turkish. Computational Linguistics, 34(3):357–389. find
9. Spence Green and Christopher D. Manning. 2010. Better Arabic parsing: Baselines, evaluations, and analysis. In Proceedings of the 23rd International Conference on Computational Linguistics (COLING), pages 394– 402, Beijing, China. find our card
10. Nizar Habash and Owen Rambow. 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), pages 573–580, Ann Arbor, Michigan. find our card
11. Nizar Habash and Ryan Roth. 2009. Catib: The columbia arabic treebank. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 221– 224, Suntec, Singapore, August. find our card
12. Nizar Habash, Reem Faraj, and Ryan Roth. 2009. Syntactic Annotation in the Columbia Arabic Treebank. In Proceedings of MEDAR International Conference on Arabic Language Resources and Tools, Cairo, Egypt. find
13. Nizar Habash. 2010. Introduction to Arabic Natural Language Processing. Morgan & Claypool Publishers. find
14. Jan Hajič and Barbora Vidová-Hladká. 1998. Tagging Inflective Languages: Prediction of Morphological Categories for a Rich, Structured Tagset. In Proceedings of the International Conference on Computational Linguistics (COLING)- the Association for Computational Linguistics (ACL), pages 483–490. find
15. Sandra Kübler, Ryan McDonald, and Joakim Nivre. 2009. Dependency Parsing. Synthesis Lectures on Human Language Technologies. Morgan and Claypool Publishers. find
16. Seth Kulick, Ryan Gabbard, and Mitch Marcus. 2006. Parsing the Arabic Treebank: Analysis and improvements. In Proceedings of the Treebanks and Linguistic Theories Conference, pages 31–42, Prague, Czech Republic. find
17. Mohamed Maamouri, Ann Bies, Timothy A. Buckwalter, and Wigdan Mekki. 2004. The Penn Arabic Treebank: Building a Large-Scale Annotated Arabic Corpus. In Proceedings of the NEMLAR Conference on Arabic Language Resources and Tools, pages 102–109, Cairo, Egypt. find
18. Yuval Marton, Nizar Habash, and Owen Rambow. 2010. Improving Arabic dependency parsing with inflectional and lexical morphological features. In Proceedings of Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL) at the 11th Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) - Human Language Technology (HLT), Los Angeles, USA. find
19. Jens Nilsson and Joakim Nivre. 2008. MaltEval: An evaluation and visualization tool for dependency parsing. In Proceedings of the sixth International Conference on Language Resources and Evaluation (LREC), Marrakech, Morocco. find
20. Joakim Nivre, Johan Hall, Jens Nilsson, Atanas Chanev, Gulsen Eryigit, Sandra Kubler, Svetoslav Marinov, and Erwin Marsi. 2007. MaltParser: A language-independent system for data-driven dependency parsing. Natural Language Engineering, 13(2):95–135. find
21. Joakim Nivre, Igor M. Boguslavsky, and Leonid K. Iomdin. 2008. Parsing the SynTagRus Treebank of Russian. In Proceedings of the 22nd International Conference on Computational Linguistics (COLING), pages 641–648. find
22. Joakim Nivre. 2003. An efficient algorithm for projective dependency parsing. In Proceedings of the 8th International Conference on Parsing Technologies (IWPT), pages 149–160, Nancy, France. find our card
23. Joakim Nivre. 2008. Algorithms for deterministic incremental dependency parsing. Computational Linguistics, 34(4). find our card
24. Joakim Nivre. 2009. Parsing Indian languages with MaltParser. In Proceedings of the ICON09 NLP Tools Contest: Indian Language Dependency Parsing, pages 12–18. find
25. Ryan Roth, Owen Rambow, Nizar Habash, Mona Diab, and Cynthia Rudin. 2008. Arabic morphological tagging, diacritization, and lemmatization using lexeme models and feature ranking. In Proceedings of ACL-08: HLT, Short Papers, pages 117–120, Columbus, Ohio, June. Association for Computational Linguistics. find our card
26. Otakar Smrž. 2007. Functional Arabic Morphology. Formal System and Implementation. Ph.D. thesis, Charles University, Prague. find
27. Reut Tsarfaty and Khalil Sima’an. 2007. Three-dimensional parametrization for parsing morphologically rich languages. In Proceedings of the 10th International Conference on Parsing Technologies (IWPT), pages 156–167, Morristown, NJ, USA. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/aclbulk-2011-marton-improving-arabic-dependency-parsing-form/