PropBank has been widely used as training data for Semantic Role Labeling. However, because this training data is taken from the WSJ, the resulting machine learning models tend to...
Abstract. We present a theory of proof denotations in classical propologic. The abstract definition is in terms of a semiring of weights, and two concrete instances are explored. ...
Software systems are subject to ever increasing complexity and in need of efficient structuring. The concept of organization as an exand abstract real-world reference presents a pr...
General-purpose ontologies (e.g. WordNet) are convenient, but they are not always scientifically valid. We draw on techniques from semantic class learning to improve the scientific...
This paper presents a new method of calculating the sematic similarity between articles based on WordNet. To further improve the performance of the proposed method, we build a new...