Paper: Joint Learning Improves Semantic Role Labeling

ACL ID P05-1073
Title Joint Learning Improves Semantic Role Labeling
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2005

Despite much recent progress on accu- rate semantic role labeling, previous work has largely used independent classifiers, possibly combined with separate label se- quence models via Viterbi decoding. This stands in stark contrast to the linguistic observation that a core argument frame is a joint structure, with strong dependen- cies between arguments. We show how to build a joint model of argument frames, incorporating novel features that model these interactions into discriminative log- linear models. This system achieves an error reduction of 22% on all arguments and 32% on core arguments over a state- of-the art independent classifier for gold- standard parse trees on PropBank.