Putting Semantics into Semantic Roles

Proceedings of the 7th Joint Conference on Lexical and Computational Semantics (*SEM), pages 235–244 New Orleans, June 5-6, 2018. c⃝2018 Association for Computational Linguistics Putting Semantics into Semantic Roles James F. Allen1,2 and Choh Man Teng1 1Institute for Human and Machine Cognition, 40 S. Alcaniz St., Pensacola FL 32502, USA 2Department of Computer Science, University of Rochester, Rochester NY 14627, USA jallen@ihmc.us, cmteng@ihmc.us Abstract While there have been many proposals for theories of semantic roles over the years, these models are mostly justified by intui- tion and the only evaluation methods have been inter-annotator agreement. We ex- plore three different ideas for providing more rigorous theories of semantic roles. These ideas give rise to more objective cri- teria for designing role sets, and lend themselves to some experimental evalua- tion. We illustrate the discussion by exam- ining the semantic roles in TRIPS. 1 Introduction Semantic roles play a foundational role in most computational approaches to encoding meaning, yet they remain surprisingly ill-defined. For the most part, a role taxonomy is defined by an in- formal gloss and some examples. In other cases, semantic roles act purely as convenient names for arguments of a predicate, frame or event, but are otherwise uninterpreted. This paper starts from the belief that if we are going to base a representation on semantic roles, they should have consequences independent of the predicate or event they are used in. In particular, we will explore three differ- ent aspects that identify criteria one might want in a theory of semantic roles: 1. Entailment: We should be able to identify en- tailments from a role independent of the type that has such roles 2. Integration with ontology: Roles should obey the typical entailments in an ontology (e.g., inheritance of properties from parents in the ontology) 3. Derivability: The roles that a type has should be derivable from its semantic properties, as revealed by definitions of the type in sources such as dictionaries. The first property helps ensure that roles are used consistently in a semantic lexicon, the second en- sures consistency with an ontology used for rea- soning, and the third evaluates the semantic inter- dependence of roles and the types they occur in. This paper will examine a particular role set, the TRIPS roles sketched in Allen & Teng, (2017)1. The first two properties are more formal in nature, but the third allows empirical evalua- tion, namely, whether the roles of an unknown word sense can be derived from its definition. 2 Preliminaries Semantic roles have a long history, originating in linguistics as thematic roles (e.g., Fillmore, 1968; Dowty, 1991) and widely adopted in computa- tional linguistics for semantic representations be- cause of their compatibility with frame-based and graph-based (i.e., semantic networks) representa- tions of meaning. Very roughly, computational approaches can be divided into two classes based on whether one be- lieves there is a single universal set of roles (e.g., LiRICS (Bunt & Rosemary, 2002; Petukhova & Bunt, 2008), VerbNet (Kipper et al., 2008; Bonial et …

Content truncated to 500 words