Semantic Role Assignment for Event Nominalisations by Leveraging Verbal Data
نویسندگان
چکیده
This paper presents a novel approach to the task of semantic role labelling for event nominalisations, which make up a considerable fraction of predicates in running text, but are underrepresented in terms of training data and difficult to model. We propose to address this situation by data expansion. We construct a model for nominal role labelling solely from verbal training data. The best quality results from salvaging grammatical features where applicable, and generalising over lexical heads otherwise.
منابع مشابه
Statistical Interpretation of Compound Nominalisations
This paper presents a method for detecting compound nominalisations from open data, and providing a semantic intepretation. It uses a statistical model based on confidence intervals over frequencies extracted from a large, balanced corpus. Using three paraphrases of the given compound nominalisation, and interpretation preferences of its components, the algorithm achieves about 70% accuracy in ...
متن کاملA semantic-aware role-based access control model for pervasive computing environments
Access control in open and dynamic Pervasive Computing Environments (PCEs) is a very complex mechanism and encompasses various new requirements. In fact, in such environments, context information should be used in access control decision process; however, it is not applicable to gather all context information completely and accurately all the time. Thus, a suitable access control model for PCEs...
متن کاملTowards constructing an Integrative, Multi-Level Model for Cognition: The Function of Semantic Networks
Integrated approaches try to connect different constructs in different theories and reinterpret them using a common conceptual framework. In this research, using the concept of processing levels, an integrated, three-level model of the cognitive systems has been proposed and evaluated. Processing levels are divided into three categories of Feature-Oriented, Semantic and Conceptual Level based o...
متن کاملStatistical Interpretation of Compound Nouns
We present a method for detecting compound nominalisations in open data, and deriving an interpretation for them. Discovering the semantic relationship between the modifier and head noun in a compound nominalisation is first construed as a twoway disamiguation task between an underlying subject or object semantic relation between a head noun and its modifier, and second as a three-way task betw...
متن کاملElectrophysiological Evidence for Use of the Animacy Hierarchy, but not Thematic Role Assignment, During Verb Argument Processing.
Animacy is known to play an important role in language processing and production, but debate remains as to how it exerts its effects: 1) through links to syntactic ordering, 2) through inherent differences between animate and inanimate entities in their salience/lexico-semantic accessibility, 3) through links to specific thematic roles. We contrasted these three accounts in two event related po...
متن کامل