Abstract

The Linked Open Data (LOD) initiative has been one of the successful manifestations of Semantic Web efforts over the last two decades, with near-exponential growth of LOD datasets in the initial years. Entities and datasets on LOD are naturally discrete, making them amenable to both well-defined reasoning and retrieval procedures that ultimately return lists or sets of resource identifiers fulfilling some criteria (whether stating user intent or using pattern-matching query languages like SPARQL). In recent years, representation learning algorithms have witnessed a powerful ascent in mainstream Artificial Intelligence, fueled in part by the adoption and refinement of neural network architectures like Recurrent Neural Nets and skip-grams, and by empirical successes such as achieved in the natural language processing and knowledge discovery communities by word and graph embeddings. Large datasets, which are almost always required by such algorithms, make it possible to train and release models openly. In some cases, open models can even be released based on proprietary datasets like Twitter corpora. We propose that the Semantic Web community position itself as a pre-eminent research leader in this space by leveraging the vast and diverse collection of structured datasets that are currently available on Linked Open Data, to build out a corresponding continuous-space equivalent.

Date

January 1, 2019

Authors

Mayank Kejriwal, Pedro A Szekely

Conference

ISWC (Satellites)

Pages

333-337