TY - UNPB
T1 - Referential Uncertainty and Word Learning in High-dimensional, Continuous Meaning Spaces
AU - Spranger, Michael
AU - Beuls, Katrien
N1 - Published as Spranger, M. and Beuls, K. (2016). Referential uncertainty and word learning in high-dimensional, continuous meaning spaces. In Hafner, V. and Pitti, A., editors, Development and Learning and Epigenetic Robotics (ICDL-Epirob), 2016 Joint IEEE International Conferences on, 2016. IEEE
PY - 2016/9/30
Y1 - 2016/9/30
N2 - 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.
AB - 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.
KW - cs.CL
M3 - Preprint
BT - Referential Uncertainty and Word Learning in High-dimensional, Continuous Meaning Spaces
ER -