Accurate and efficient non-projective dependency parsing

• Applicant: Professor Marco Kuhlmann, Ph.D.
• Subject Area: Security and Dependability, Operating-, Communication- and Distributed Systems
• Term: Funded in 2008
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 72394720

The goal of the proposed research project is to develop accurate and efficient methods for non-projective, data-driven dependency parsing. The purpose of parsing is the automatic analysis of the syntactic structure of natural language. Data-driven dependency parsing is distinguished from other approaches in that it employs syntactic representations based on word-to-word dependencies, and makes essential use of empirical data. Most of the previous work on dependency parsing has been confined to dependency analyses that satisfy a structural constraint called projectivity. While this facilitates efficient computations, it does so at the cost of accuracy, as it rules out many analyses that occur in the data. Recent work has tried to identify classes of dependency structures that strike a better balance between accuracy and efficiency. In this project, I will develop and evaluate a data-driven parsing framework for such ‘mildly’ non-projective dependency structures. The project is the first comprehensive investigation of parsing methods based on these structures.

• DFG Programme: Research Fellowships
• International Connection: Sweden