Year: 2015
Type: conference-paper
Abstract: We describe a semantic role labeler with stateof-the-art performance and low computational requirements, which uses convolutional and time-domain neural networks.The system is designed to work with features derived from a dependency parser output.Various system options and architectural details are discussed.Incremental experiments were run to explore the benefits of adding increasingly more complex dependency-based features to the system; results are presented for both in-domain and out-of-domain datasets.
DOI: 10.18653/v1/s15-1033
Authors: William Foland, James Martin
Institutions: University of Colorado Boulder, University of Colorado System
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2156432050