Automatic Labeling of Semantic Roles

TitleAutomatic Labeling of Semantic Roles
Publication TypeTechnical Report
Year of Publication2001
AuthorsGildea, D., & Jurafsky D.
Other Numbers1192

We present a system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame. Given an input sentence, the system labels constituents with either abstract semantic roles such as Agent or Patient, or more domain-specific semantic roles such as Speaker, Message, and Topic. The system is based on statistical classifiers which were trained on 653 semantic role types from roughly 50,000 sentences. Each sentence had been hand-labeled with semantic roles in the FrameNet semantic labeling project. We compare the usefulness of different features and feature-combination methods in the semantic role labeling task.

Bibliographic Notes

ICSI Technical Report TR-01-005

Abbreviated Authors

D. Gildea and D. Jurafsky

ICSI Research Group


ICSI Publication Type

Technical Report