Search Results for author:
Found 7 papers, 0 papers with code
Text-Based Joint Prediction of Numeric and Categorical Attributes of Entities in Knowledge Bases
Our analysis indicates that this is the case because categorical attributes, many of which describe membership in various classes, provide useful {`}background knowledge{'} for numeric prediction, while this is true to a lesser degree in the inverse direction.
Instantiation
Our paper closes this gap by investigating and modeling the lexical relation of instantiation, which holds between an entity-denoting and a category-denoting expression (Marie Curie -- scientist or Mumbai -- city).
Distributed Prediction of Relations for Entities: The Easy, The Difficult, and The Impossible
Word embeddings are supposed to provide easy access to semantic relations such as {``}male of{''} (man{--}woman).
Instances and concepts in distributional space
Instances ({``}Mozart{''}) are ontologically distinct from concepts or classes ({``}composer{''}).
