This paper is a description of our system for SemEval-2015 Task 18: Broad-Coverage Semantic Dependency Parsing. We implement a hybrid parser which benefits from both transition-based and graph-based parsing approaches. In particular, the tree approximation method is explored to take advantage of well-studied tree parsing techniques. Evaluation on multilingual data sets demonstrates that considerably good semantic analysis can be automatically built by applying state-of-the-art data-driven parsing techniques.
展开▼