Semantic maps can visually display a word or phrase and a set of related words or concepts. They can be an alternative to random mapping, principal components analysis, and latent semantic indexing methods. Inside Big Data brought this interesting information to our attention in their article, “Best of arXiv.org for AI, Machine Learning, and Deep Learning – August 2018.”
The problems arising in semantic mapping are the same as in data mapping for data integration purposes. The difference is that here the semantic relationships are made explicit through the use of semantic nets or ontologies which play the role of data dictionaries in data mapping.
For intelligent robots to interact in meaningful ways with their environment they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping challenges separately, focusing on either geometric or semantic mapping. The problem of building environmental maps that include both semantically meaningful, object-level entities and point-or mesh-based geometrical representations still exists.
Melody K. Smith
Sponsored by Access Innovations, the world leader in taxonomies, metadata, and semantic enrichment to make your content findable.
