Year: 2009
Type: conference-paper
Abstract: We describe an unsupervised system for learning narrative schemas, coherent sequences or sets of events (arrested(POLICE, SUSPECT), convicted(JUDGE, SUSPECT)) whose arguments are filled with participant semantic roles defined over words (Judge = {judge, jury, court}, Police = {police, agent, authorities}). Unlike most previous work in event structure or semantic role learning, our system does not use supervised techniques, hand-built knowledge, or predefined classes of events or roles. Our unsupervised learning algorithm uses coreferring arguments in chains of verbs to learn both rich narrative event structure and argument roles. By jointly addressing both tasks, we improve on previous results in narrative/frame learning and induce rich frame-specific semantic roles.
Authors: Nathanael Chambers, Dan Jurafsky
Institution: Stanford University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funder: National Science Foundation
OpenAlex ID: W2158794898
