Abstract | We apply our simplification system to semantic role labeling (SRL). |
Experiments | We evaluated our system using the setup of the Conll 2005 semantic role labeling task.2 Thus, we trained on Sections 2-21 of PropBank and used Section 24 as development data. |
Introduction | In semantic role labeling (SRL), given a sentence containing a target verb, we want to label the semantic arguments, or roles, of that verb. |
Introduction | Current semantic role labeling systems rely primarily on syntactic features in order to identify and |
Probabilistic Model | This allows us to learn that “give” has a preference for the labeling {ARGO = Subject NP, ARGI = Postverb NP2, ARGZ = Postverb NP1 Our final features are analogous to those used in semantic role labeling , but greatly simplified due to our use of simple sentences: head word of the constituent; category (i.e., constituent label); and position in the simple sentence. |
Related Work | Another area of related work in the semantic role labeling literature is that on tree kernels (Moschitti, 2004; Zhang et al., 2007). |
Abstract | This paper presents an empirical study on the robustness and generalization of two alternative role sets for semantic role labeling : PropBank numbered roles and VerbNet thematic roles. |
Experimental Setting 3.1 Datasets | Our basic Semantic Role Labeling system represents the tagging problem as a Maximum Entropy Markov Model (MEMM). |
Introduction | Semantic Role Labeling is the problem of analyzing clause predicates in open text by identifying arguments and tagging them with semantic labels indicating the role they play with respect to the verb. |