Referential Uncertainty and Word Learning in High-dimensional, Continuous Meaning Spaces

This paper discusses lexicon word learning in high-dimensional meaning spaces\nfrom the viewpoint of referential uncertainty. We investigate various\nstate-of-the-art Machine Learning algorithms and discuss the impact of scaling,\nrepresentation and meaning space structure. We demonstrate that current Machine\nLearning techniques successfully deal with high-dimensional meaning spaces. In\nparticular, we show that exponentially increasing dimensions linearly impact\nlearner performance and that referential uncertainty from word sensitivity has\nno impact.\n