Statistical Models for Frame-Semantic Parsing

摘要

We present a brief history and overview of statistical methods in frame-semantic parsing - the automatic analysis of text using the theory of frame semantics. We discuss how the FrameNet lexicon and frame-annotated datasets have been used by statistical NLP researchers to build usable, state-of-the-art systems. We also focus on future directions in frame-semantic parsing research, and discuss NLP applications that could benefit from this line of work.