Referential Uncertainty and Word Learning in High-dimensional, Continuous Meaning Spaces
This addresses the challenge of scaling word learning models for computational linguistics, but it appears incremental as it evaluates existing methods rather than introducing new ones.
The paper tackled the problem of lexicon word learning in high-dimensional meaning spaces by investigating referential uncertainty, showing that current machine learning techniques handle high dimensions effectively, with exponentially increasing dimensions linearly impacting performance and referential uncertainty having no impact.
This paper discusses lexicon word learning in high-dimensional meaning spaces from the viewpoint of referential uncertainty. We investigate various state-of-the-art Machine Learning algorithms and discuss the impact of scaling, representation and meaning space structure. We demonstrate that current Machine Learning techniques successfully deal with high-dimensional meaning spaces. In particular, we show that exponentially increasing dimensions linearly impact learner performance and that referential uncertainty from word sensitivity has no impact.