Class-Based Construction of a Verb Lexicon
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Hybrid Natural Language Generation from Lexical Conceptual Structures
Machine Translation
Semantic role labeling: an introduction to the special issue
Computational Linguistics
Hi-index | 0.00 |
Widely accepted resources for semantic parsing, such as PropBank and FrameNet, are not perfect as a semantic role labeling framework. Their semantic roles are not strictly defined; therefore, their meanings and semantic characteristics are unclear. In addition, it is presupposed that a single semantic role is assigned to each syntactic argument. This is not necessarily true when we consider internal structures of verb semantics. We propose a new framework for semantic role annotation which solves these problems by extending the theory of lexical conceptual structure (LCS). By comparing our framework with that of existing resources, including VerbNet and FrameNet, we demonstrate that our extended LCS framework can give a formal definition of semantic role labels, and that multiple roles of arguments can be represented strictly and naturally.