Elamur Research⌕
☰
home / papers / 2008 / Dependency Parsing of Turkish

Dependency Parsing of Turkish

Paper · 2008 · Gülşen Eryiğit, Joakim Nivre and Kemal Oflazer

Summary

The paper asks how well data-driven dependency parsing works for Turkish, a language with agglutinative morphology, flexible constituent order and mostly head-final structure. Turkish stands in for a broader family of languages that differ sharply from English. Using the Turkish Treebank (the CoNLL-X release), the authors compare two kinds of parsing units. One treats whole word forms as nodes. The other treats inflectional groups (IGs) as nodes: these are sublexical chunks split at derivational boundaries, and each carries its own part of speech and features. They test both representations with two parsers. The first is a probabilistic parser with beam search. The second is a deterministic, classifier-based parser built in the MaltParser framework. They also measure how morphological features and lexicalization affect accuracy, and they repeat the evaluation with automatic morphological disambiguation instead of gold tags. IG-based models beat word-based ones under every setting tested. The best configuration combines the classifier-based parser with IGs, inflectional features and lexical information, and it gives the highest reported accuracy on this treebank. The results show that parsers for morphologically rich languages should model sub-word structure.

Key points

  • The data is the Turkish Treebank (Oflazer et al. 2003), built by METU and Sabancı University. Its sentences make up only a limited portion of the larger Metu Turkish Corpus, whose texts date from after 1990 and span 10 genres.
  • Dependencies are annotated between IGs. A link leaves from the last IG of the dependent word and points to a specific IG of the head word. For this reason the authors argue that IG-to-IG accuracy is the correct metric.
  • Morphological features raised accuracy for both parsers, but the probabilistic parser needed careful feature selection to cope with sparse data. Lexicalization helped only the classifier-based parser.
  • In the CoNLL-X shared task on Turkish, the top system was Nivre et al. (2006), with unlabeled attachment of 75.8 and labeled attachment of 65.7. The average labeled score was 55.4, and the systems below average generally ignored inflectional features.
  • Çakıcı and Baldridge (2006) used MSTParser and reported 84.9% word-to-word accuracy. That figure cannot be compared with the others because it does not rest on an official treebank release and uses a different evaluation setup.

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

🎓Uppsala UniversityUppsala · Sweden56 works · 13,046 citations🎓Istanbul Technical UniversityIstanbul · Türkiye8 works · 2,996 citations

Also on the byline: Sabancı Üniversitesi.

📚 Shelves 4 Computer Science · 9,086 works Artificial Intelligence · 8,889 works Arts and Humanities · 9,296 works Language and Linguistics · 9,206 works

🧭 Topics 2 Dependency parsing · 120 works Morphology · 277 works

Cite

Cite as Gülşen Eryiğit, Joakim Nivre and Kemal Oflazer. 2008. Dependency Parsing of Turkish. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli.2008.07-017-r1-06-83

@article{eryigit2008dependency,
  title = {{Dependency Parsing of Turkish}},
  author = {Gülşen Eryiğit, Joakim Nivre and Kemal Oflazer},
  journal = {Computational Linguistics},
  year = {2008},
  doi = {10.1162/coli.2008.07-017-r1-06-83},
  url = {https://doi.org/10.1162/coli.2008.07-017-r1-06-83}
}

References

67 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Arun, Abhishek and Frank Keller. 2005. Lexicalization in crosslinguistic probabilistic parsing: The case of French. In Proceedings of ACL’05, pages 302–313, Ann Arbor, MI. find
  2. Attardi, Giuseppe. 2006. Experiments with a multilanguage non-projective dependency parser. In Proceedings of CONLL-X, pages 166–170, New York, NY.
  3. Bick, Eckhard. 2006. Lingpars, a linguistically inspired, language-independent machine learner for dependency treebanks. In Proceedings of CONLL-X, pages 171–175, New York, NY. find
  4. Bikel, Daniel M. 2004. A distributional analysis of a lexicalized statistical parsing model. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 182–189, Barcelona. find
  5. Bikel, Daniel M. and David Chiang. 2000. Two statistical parsing models applied to the Chinese treebank. In Proceedings of the 2nd Chinese Language Processing Workshop, pages 1–6, Hong Kong. find
  6. Black, Ezra, Frederick Jelinek, John D. Lafferty, David M. Magerman, Robert L. Mercer, and Salim Roukos. 1992. Towards history-based grammars: Using richer models for probabilistic parsing. In Proceedings of the 5th DARPA Speech and Natural Language Workshop, pages 31–37, New York, NY.
  7. Bozşahin, Cem. 2002. The combinatory morphemic lexicon. Computational Linguistics, 28(2):145–186. find
  8. Buchholz, Sabine and Erwin Marsi. 2006. CONLL-X shared task on multilingual dependency parsing. In Proceedings of CONLL-X, pages 149–164, New York, NY.
  9. Çakıcı, Ruket and Jason Baldridge. 2006. Projective and non-projective Turkish parsing. In Proceedings of the 5th International Treebanks and Linguistic Theories Conference, pages 43–54, Prague. find
  10. Canisius, Sander, Toine Bogers, Antal van den Bosch, Jeroen Geertzen, and Erik Tjong Kim Sang. 2006. Dependency parsing by inference over high-recall dependency predictions. In Proceedings of CONLL-X, pages 176–180, New York, NY. find
  11. Carreras, Xavier, Mihai Surdeanu, and Lluis Marquez. 2006. Projective dependency parsing with perceptron. In Proceedings of CONLL-X, pages 181–185, New York, NY. find
  12. Chang, Chih-Chung and Chih-Jen Lin, 2001. LIBSVM: A Library for Support Vector Machines. Software available at www.csie.ntu.edu.tw/ ∼ cjlin/libsvm. find
  13. Chang, Ming-Wei, Quang Do, and Dan Roth. 2006. A pipeline model for bottom-up dependency parsing. In Proceedings of CONLL-X, pages 186–190, New York, NY. find
  14. Cheng, Yuchang, Masayuki Asahara, and Yuji Matsumoto. 2006. Multi-lingual dependency parsing at NAIST. In Proceedings of CONLL-X, pages 191–195, New York, NY. find
  15. Chung, Hoojung and Hae-Chang Rim. 2004. Unlexicalized dependency parser for variable word order languages based on local contextual pattern. In Proceedings of the 5th International Conference on Intelligent Text Processing and Computational Linguistics, pages 109–120, Seoul. find
  16. Collins, Michael. 1996. A new statistical parser based on bigram lexical dependencies. In Proceedings of ACL’96, pages 184–191, Santa Cruz, CA. find
  17. Collins, Michael. 1997. Three generative, lexicalised models for statistical parsing. In Proceedings of ACL’97, pages 16–23, Madrid.
  18. Collins, Michael. 1999. Head-Driven Statistical Models for Natural Language Parsing. Ph.D. thesis, University of Pennsylvania, Philadelphia. find
  19. Collins, Michael, Jan Hajic, Lance Ramshaw, and Christoph Tillmann. 1999. A statistical parser for Czech. In Proceedings of ACL’99, pages 505–518, College Park, MD.
  20. Corazza, Anna, Alberto Lavelli, Giorgio Satta, and Roberto Zanoli. 2004. Analyzing an Italian treebank with state-of-the-art statistical parsers. In Proceedings of the 3rd Workshop on Treebanks and Linguistic Theories, pages 39–50, Tübingen. find
  21. Corston-Oliver, Simon and Anthony Aue. 2006. Dependency parsing with reference to Slovene, Spanish and Swedish. In Proceedings of CONLL-X, pages 196–200, New York, NY. find
  22. Daelemans, Walter and Antal Vanden Bosch. 2005. Memory-Based Language Processing. Cambridge University Press, Cambridge. find
  23. Dreyer, Markus, David A. Smith, and Noah A. Smith. 2006. Vine parsing and minimum risk reranking for speed and precision. In Proceedings of CONLL-X, pages 201–205, New York, NY. find
  24. Dubey, Amit and Frank Keller. 2003. Probabilistic parsing for German using sister-head dependencies. In Proceedings of ACL’03, pages 96–103, Sapporo. find
  25. Eisner, Jason. 1996. Three new probabilistic models for dependency parsing: An exploration. In Proceedings of the 16th International Conference on Computational Linguistics, pages 340–345, Copenhagen.
  26. Erguvanlı, Eser Emine. 1979. The Function of Word Order in Turkish Grammar. Ph.D. thesis, UCLA. find
  27. Eryiğit, Gülşen. 2006. Türkçenin Bağlılık Ayrıştırması (Dependency Parsing of Turkish). Ph.D. thesis, Istanbul Technical University. find
  28. Eryiğit, Gülşen, Eşref Adalı, and Kemal Oflazer. 2006. Türkçe cümlelerin kural tabanlı bağlılık analizi [Rule-based dependency parsing of Turkish sentences]. In Proceedings of the 15th Turkish Symposium on Artificial Intelligence and Neural Networks, pages 17–24, Muğla. find
  29. Eryiğit, Gülşen, Joakim Nivre, and Kemal Oflazer. 2006. The incremental use of morphological information and lexicalization in data-driven dependency parsing. In Computer Processing of Oriental Languages, Beyond the Orient: The Research Challenges Ahead, pages 498–507, Singapore. find
  30. Eryiğit, Gülşen and Kemal Oflazer. 2006. Statistical dependency parsing of Turkish. In Proceedings of EACL’06, pages 89–96, Trento. find
  31. Gildea, Daniel. 2001. Corpus variation and parser performance. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 167–202, Pittsburgh, PA.
  32. Hajič, Jan, Eva Hajičová, Petr Pajas, Jarmila Panevová, Petr Sgall, and Barbora Hladká. 2001. Prague dependency treebank 1.0 (final production label). CDROM CAT: LDC2001T10., ISBN 1-58563-212-0. find
  33. Hakkani-Tür, Dilek, Kemal Oflazer, and Gökhan Tür. 2002. Statistical morphological disambiguation for agglutinative languages. Journal of Computers and Humanities, 36(4):381–410. find
  34. Hoffman, Beryl. 1994. Generating context appropriate word orders in Turkish. In Proceedings of the Seventh International Workshop on Natural Language Generation, pages 117–126, Kennebunkport, ME. find
  35. Johansson, Richard and Pierre Nugues. 2006. Investigating multilingual dependency parsing. In Proceedings of CONLL-X, pages 206–210, New York, NY. find
  36. Klein, Dan and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of ACL’03, pages 423–430, Sapporo.
  37. Kromann, Matthias T. 2003. The Danish dependency treebank and the underlying linguistic theory. In Proceedings of the 2nd Workshop on Treebanks and Linguistic Theories, pages 217–220, Växjö. find
  38. Kudo, Taku and Yuji Matsumoto. 2002. Japanese dependency analysis using cascaded chunking. In Proceedings of the Conference on Computational Natural Language Learning, pages 63–69, Taipei. find
  39. Levy, Roger and Christopher Manning. 2003. Is it harder to parse Chinese, or the Chinese treebank? In Proceedings of ACL’03, pages 439–446, Sapporo. find
  40. Liu, Ting, Jinshan Ma, Huijia Zhu, and Sheng Li. 2006. Dependency parsing based on dynamic local optimization. In Proceedings of CONLL-X, pages 211–215, New York, NY. find
  41. Magerman, David M. 1995. Statistical decision-tree models for parsing. In Proceedings of ACL’95, pages 276–283, Cambridge, MA.
  42. Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English: The Penn treebank. Computational Linguistics, 19(2):313–330.
  43. McDonald, Ryan, Kevin Lerman, and Fernando Pereira. 2006. Multilingual dependency analysis with a two-stage discriminative parser. In Proceedings of CONLL-X, pages 216–220, New York, NY.
  44. Nivre, Joakim. 2003. An efficient algorithm for projective dependency parsing. In Proceedings of the 8th International Workshop on Parsing Technologies, pages 149–160, Nancy.
  45. Nivre, Joakim. 2004. Incrementality in deterministic dependency parsing. In Proceedings of the Workshop on Incremental Parsing: Bringing Engineering and Cognition Together, pages 50–57, Barcelona.
  46. Nivre, Joakim. 2006. Inductive Dependency Parsing. Springer, Dordrecht. find
  47. Nivre, Joakim, Johan Hall, and Jens Nilsson. 2004. Memory-based dependency parsing. In Proceedings of the Conference on Computational Natural Language Learning, pages 49–56, Boston, MA.
  48. Nivre, Joakim, Johan Hall, Jens Nilsson, Atanas Chanev, Gülşen Eryiğit, Sandra Kübler, Stetoslav Marinov, and Erwin Marsi. 2007. Maltparser: A language-independent system for data-driven dependency parsing. Natural Language Engineering Journal, 13(2):95–135. find
  49. Nivre, Joakim, Johan Hall, Jens Nilsson, Gülşen Eryiğit, and Stetoslav Marinov. 2006. Labeled pseudo-projective dependency parsing with support vector machines. In Proceedings of CONLL-X, pages 221–225, New York, NY.
  50. Nivre, Joakim and Jens Nilsson. 2005. Pseudo-projective dependency parsing. In Proceedings of ACL’05, pages 99–106, Ann Arbor, MI.
  51. Nivre, Joakim, Jens Nilsson, and Johan Hall. 2006. Talbanken05: A Swedish treebank with phrase structure and dependency annotation. In Proceedings of LREC, pages 1392–1395, Genoa.
  52. Oflazer, Kemal. 1994. Two-level description of Turkish morphology. Literary and Linguistic Computing, 9(2):137–148.
  53. Oflazer, Kemal. 2003. Dependency parsing with an extended finite-state approach. Computational Linguistics, 29(4):515–544. find
  54. Oflazer, Kemal, Bilge Say, Dilek Z. Hakkani-Tür, and Gökhan Tür. 2003. Building a Turkish treebank. In A. Abeillé, editor, Treebanks: Building and Using Parsed Corpora. Kluwer, London, pages 261–277. find
  55. Ratnaparkhi, Adwait. 1997. A linear observed time statistical parser based on maximum entropy models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1–10, Providence, RI.
  56. Riedel, Sebastian, Ruket Çakıcı, and Ivan Meza-Ruiz. 2006. Multi-lingual dependency parsing with incremental integer linear programming. In Proceedings of CONLL-X, pages 226–230, New York, NY. find
  57. Sagae, Kenji and Alon Lavie. 2005. A classifier-based parser with linear run-time complexity. In Proceedings of the 9th International Workshop on Parsing Technologies, pages 125–132, Vancouver.
  58. Schiehlen, Michael and Kristina Spranger. 2006. Language independent probabilistic context-free parsing bolstered by machine learning. In Proceedings of CONLL-X, pages 231–235, New York, NY. find
  59. Sekine, Satoshi, Kiyotaka Uchimoto, and Hitoshi Isahara. 2000. Backward beam search algorithm for dependency analysis of Japanese. In Proceedings of the 17th International Conference on Computational Linguistics, pages 754–760, Saarbrücken. find
  60. Shimizu, Nobuyuki. 2006. Maximum spanning tree algorithm for non-projective labeled dependency parsing. In Proceedings of CONLL-X, pages 236–240, New York, NY. find
  61. Simov, Kiril, Gergana Popova, and Petya Osenova. 2002. HPSG-based syntactic treebank of Bulgarian (BulTreeBank). In Andrew Wilson, Paul Rayson, and Tony McEnery, editors, A Rainbow of Corpora: Corpus Linguistics and the Languages of the World. Lincom-Europa, Munich, pages 135–142. find
  62. Vapnik, Vladimir N. 1995. The Nature of Statistical Learning Theory. Springer, New York, NY. find
  63. Wu, Yu-Chieh, Yue-Shi Lee, and Jie-Chi Yang. 2006. The exploration of deterministic and efficient dependency parsing. In Proceedings of CONLL-X, pages 241–245, New York, NY. find
  64. Yamada, Hiroyasu and Yuji Matsumoto. 2003. Statistical dependency analysis with support vector machines. In Proceedings of the 8th International Workshop on Parsing Technologies, pages 195–206, Nancy.
  65. Yüret, Deniz. 2006. Dependency parsing as a classification problem. In Proceedings of CONLL-X, pages 246–250, New York, NY. find
  66. Yüret, Deniz and Ferhan Türe. 2006. Learning morphological disambiguation rules for Turkish. In Proceedings of HLT/NAACL’06, pages 328–334, New York, NY. find
  67. This article has been cited by: find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/eryigit-2008-dependency-parsing-turkish/