A dependency parser of Korean based on connectionist/symbolic techniques

  • Jong -Hyeok Lee
  • Geunbae Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 990)

Abstract

This paper suggests a hybrid method for dependency parser of Korean which integrates both connectionist and symbolic techniques. First, the dependency parser tries to identify syntactic dependencies between individual words, specifying the grammatical role of dependency in each case. In most normal cases, a symbolic approach can work well, but a connectionist approach is also used for handling the cases where case-markers are omitted in a sentence. All the plausible dependencies are kept in a Syntactic Dependency Graph (SDG). Then, structural disambiguation is carried out by a constraint satisfaction process, in which various constraints on dependency structure are propagated through SDG to filter out inconsistent dependencies. For an efficient control mechanism, a forward checking algorithm is used together with both variable-ordering and value-ordering heuristics. Finally, the experiment showed very promising results with parsing accuracy of above 90% for sentences of less than 10 Korean words.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Covington, M. A.: A Dependency Parser for Variable-Word-Order Languages. Research Report AI-1990-01, Artificial Intelligence Programs, Univ. of Georgia, (1990)Google Scholar
  2. 2.
    Wermter, S., Lehnert, W. G.: A Hybrid Symbolic/Connectionist Model for Noun Phrase Understanding. In N. Sharkey(ed) it Connectionist Natural Language Processing: Readings from Connection science. London: Kluwer Academic Publishers (1992) 101–118Google Scholar
  3. 3.
    Kodama, T.: Studies in Dependency Grammar. Tokyo: Kenkyusha (1987) (written in Japanese).Google Scholar
  4. 4.
    Melcuk, I. A.: Dependency Syntax: Theory and Practice. New York: State University of New York Press (1988)Google Scholar
  5. 5.
    Maruyama, H.: Structural Disambiguation with Constraint Propagation. Proceedings of the 28th Annual Meeting of the ACL (1990) 31–38Google Scholar
  6. 6.
    Robinson, J. J.: Dependency Structures and Transformation Rules. Languages 46 (1970) 259–285Google Scholar
  7. 7.
    Seo, J., Simmons, R.: Syntactic Graphs: a Representation for the Union of All Ambiguous Parse Trees. Computational Linguistics 15(7) (1988) 19–32Google Scholar
  8. 8.
    Kumar, V.: Algorithms for Constraint-Satisfaction Problems: A Survey. AI Magazine Spring (1992) 32–44Google Scholar
  9. 9.
    Haralick, R., Elliot, G.: Increasing Tree Search Efficiency for Constraint-Satisfaction Problems. Artificial Intelligence 14(3) (1980) 263–313CrossRefGoogle Scholar
  10. 10.
    Bitner, J., Reingold, E. M.: Backtrack Programming Techniques 18 (1975) 651–655Google Scholar
  11. 11.
    Chang, S.: Information-Based Korean Grammar. Seoul: Language & Information Research Assn. (1993) (written in Korean)Google Scholar

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  • Jong -Hyeok Lee
    • 1
  • Geunbae Lee
    • 1
  1. 1.Department of Computer SciencePohang University of Science and TechnologyPohangKorea

Personalised recommendations