The Incremental Use of Morphological Information and Lexicalization in Data-Driven Dependency Parsing
- Gülşen EryiğitAffiliated withDepartment of Computer Engineering, Istanbul Technical Univ.
- , Joakim NivreAffiliated withSchool of Mathematics and Systems Engineering, Växjö Univ.
- , Kemal OflazerAffiliated withFaculty of Engineering and Natural Sciences, Sabancı Univ.
Typological diversity among the natural languages of the world poses interesting challenges for the models and algorithms used in syntactic parsing. In this paper, we apply a data-driven dependency parser to Turkish, a language characterized by rich morphology and flexible constituent order, and study the effect of employing varying amounts of morpholexical information on parsing performance. The investigations show that accuracy can be improved by using representations based on inflectional groups rather than word forms, confirming earlier studies. In addition, lexicalization and the use of rich morphological features are found to have a positive effect. By combining all these techniques, we obtain the highest reported accuracy for parsing the Turkish Treebank.
- The Incremental Use of Morphological Information and Lexicalization in Data-Driven Dependency Parsing
- Book Title
- Computer Processing of Oriental Languages. Beyond the Orient: The Research Challenges Ahead
- Book Subtitle
- 21st International Conference, ICCPOL 2006, Singapore, December 17-19, 2006. Proceedings
- pp 498-508
- Print ISBN
- Online ISBN
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- Series ISSN
- Springer Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- Additional Links
- Industry Sectors
- Editor Affiliations
- 18. Graduate School of Information Science, Nara Institute of Science and Technology
- 19. Dept of ECE, University of Illinois at Urbana Champaign
- 20. Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong
- 21. State Key Lab of Intelligent Tech. & Sys., Tsinghua University
- Author Affiliations
- 22. Department of Computer Engineering, Istanbul Technical Univ., 34469, Turkey
- 23. School of Mathematics and Systems Engineering, Växjö Univ., 35195, Sweden
- 24. Faculty of Engineering and Natural Sciences, Sabancı Univ., 34956, Turkey
To view the rest of this content please follow the download PDF link above.