Semantic Role Labeling Via Generalized Inference Over Classifiers
Abstract
We present a system submitted to the CoNLL-2004 shared task for semantic role labeling. The system is composed of a set of classifiers and an inference procedure used both to clean the classification results and to ensure structural integrity of the final role labeling. Linguistic information is used to generate features during classification and constraints for the inference process. Semantic role labeling is a complex task to discover patterns within sentences corresponding to semantic meaning. We believe it is hopeless to expect high levels of performance from either purely manual classifiers or purely learned classifiers. Rather, supplemental linguistic information must be used to support and correct a learning system. The system we present here is composed of two phases.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2004
- Accession Number
- ADA457895
Entities
People
- Dan Roth
- Dav Zimak
- Vasin Punyakanok
- Wen-tau Yih
Organizations
- University of Illinois Urbana–Champaign