Machine Learning for Automatic Labeling of Frames and Frame Elements in Text

Abstract

The development of systems that extract a frame representation of text can lead to deeper semantics being used in natural language processing. We present the development of our system for extracting frames from text. Our system is trained on the FrameNet data and tested on the SemEval 2007: Task 19 Frame Extraction Task data. We use machine learning for labeling frames and frame elements, resulting in system with a good performance. We provide a detailed analysis of our methods, challenges, and results. We also provide enough details and analysis to allow other researchers to develop similar systems.