Probes are models devised to investigate the encoding of knowledge---e.g. syntactic structure---in contextual representations. Probes are often designed for simplicity, which has led to restrictions on probe design that may not allow for the full exp
loitation of the structure of encoded information; one such restriction is linearity. We examine the case of a structural probe (Hewitt and Manning, 2019), which aims to investigate the encoding of syntactic structure in contextual representations through learning only linear transformations. By observing that the structural probe learns a metric, we are able to kernelize it and develop a novel non-linear variant with an identical number of parameters. We test on 6 languages and find that the radial-basis function (RBF) kernel, in conjunction with regularization, achieves a statistically significant improvement over the baseline in all languages---implying that at least part of the syntactic knowledge is encoded non-linearly. We conclude by discussing how the RBF kernel resembles BERT's self-attention layers and speculate that this resemblance leads to the RBF-based probe's stronger performance.
This paper presents the measurements results of the velocity field of a flow
with vortical character behind a cylindrical model with a semispherical
head. Three different measuring methods have been used, i.e.: Laser –
Doppler – Anemometer (LDA),
Hotwire – Anemometer and Five – Hole –
Pressure -Probe.
A comparison between the obtained experimental results has been made
aiming to specify the accuracy and reliability of the velocity values,
measured by means of the a. m. three methods, and accordingly to
determine the reliable measurement range of each of these methods, taking
into consideration that the LDA – measurements results are the more
accurate and reliable ones, since LDA does not create any disturbances of
the flow field.