Leveraging Heterogeneous Data Sources for Relational Semantic Parsing

A number of semantic annotation efforts have produced a variety of annotated corpora, capturing various aspects of semantic knowledge in different formalisms. Due to to the cost of these annotation efforts and the relatively small amount of semantically annotated corpora, we argue it is advantageous to be able to leverage as much annotated data as possible. This work presents a preliminary exploration of the opportunities and challenges of learning semantic parsers from heterogeneous semantic annotation sources. We primarily focus on two semantic resources, FrameNet and PropBank, with the goal of improving frame-semantic parsing. Our analysis of the two data sources highlights the benefits that can be reaped by combining information across them.