Gavagai presents a poster on Semantic Topology at this week’s ACM sponsored CIKM conference on information and knowledge management, in Shanghai.
The poster is based on recent experiments by KTH students Martin Bohman, Ariel Ekgren, Gabriel Isheden, Emelie Kullmann, and David Nilsson, and supervised by Jussi Karlgren. The experiments show the usefulness of using computational topology as a tool for working with semantic spaces.
This publication marks the first public steps of moving from a black-box view of learning language models to more explicit knowledge representation. We will be continuing in this direction with further experiments, moving from academic experiments to mechanisms with direct results for the functionality of our core system.
Later this week Jussi Karlgren will also co-chair the annually recurring workshop on Semantic Annotation of Information Retrieval (ESAIR), this year in its seventh edition.
