A Hierarchical Unification of LIRICS and VerbNet Semantic Roles

Abstract

Abstract-This research compares several of the thematic roles of VerbNet (VN) to those of the Linguistic InfRastructure for Interoperable ResourCes and Systems (LIRICS). The purpose of this comparison is to develop a standard set of thematic roles that would be suited to a variety of natural language processing (NLP) applications. We draw from both resources to construct a unified set of semantic roles that will replace existing VN semantic roles. Through the process of comparison, we find that a hierarchical organization of coarse-grained, intermediate and fine-grained roles facilitates mapping between semantic resources of differing granularity and allows for flexibility in how VN can be used for diverse NLP applications; thus, we propose a hierarchical taxonomy of the unified roleset. The comparison and subsequent development of the hierarchy reveals a level of granularity shared by both resources, which could be further developed into a standard set of thematic roles for the International Organization for Standardization (ISO).

Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics

“…Very roughly, computational approaches can be divided into two classes based on whether one believes there is a single universal set of roles (e.g., LiRICS (Bunt & Rosemary, 2002;Petukhova & Bunt, 2008), VerbNet (Kipper et al, 2008;Bonial et al, 2011)), or whether one believes each type may identify its own unique roles (e.g., FrameNet ). Straddling a middle ground is PropBank , which uses a universal set of role names, but allows each type to define what their roles mean.…”

Double Trouble: The Problem of Construal in Semantic Annotation of Adpositions

“…The 75 supersenses are organized in a taxonomy based on that of VerbNet (Bonial et al, 2011), with PARTICIPANT, CIRCUMSTANCE, and CONFIGU-RATION at the top level.…”

Verb similarity: Comparing corpus and psycholinguistic data

“…A different approach is the one found in Dowty (1991), which regards semantic roles not as clear-cut categories, but rather as sets of properties or entailments that are associated to two proto-roles (Proto-Agent and Proto-Patient). Finally, we find the framework proposed by LIRICS (Bonial et al 2011), whose aim is to develop a standard roleset suitable for the different needs of various natural language processing tasks. They propose a hierarchical organization of roles based on different levels of granularity (coarse-grained roles, e.g.…”