Poplack (1993: 255) defines code-switching as the juxtaposition of multi-word sequences, each of which is internally consistent with the grammatical patterns of its respective language. Thus, in code-switching, the patterns of each language are maintained, as bilinguals switch between— not ‘mix’—their two languages (cf. Haugen 1950). Some, however, have claimed that codeswitching can have an ef...

We propose a neural embedding algorithm called Network Vector, which learns distributed representations of nodes and the entire networks simultaneously. By embedding networks in a lowdimensional space, the algorithm allows us to compare networks in terms of structural similarity and to solve outstanding predictive problems. Unlike alternative approaches that focus on node level features, we lea...

We study the role of the second language in bilingual word embeddings in monolingual semantic evaluation tasks. We find strongly and weakly positive correlations between down-stream task performance and second language similarity to the target language. Additionally, we show how bilingual word embeddings can be employed for the task of semantic language classification and that joint semantic sp...

A new method for the classification of the QRS patterns in electrocardiograms (ECGs), which belongs to the category of the syntactic methods, is presented in this paper. This method takes into account structural as well as quanlitative information. Some experimental results obtained by this method are also presented. Key wor~L~" Classification, QRS patterns, ECG waveforms, syntactic methods, st...

This study compared the effect of two types of interventions on subsequent student performance with a target synthesis problem. Students either solved two single-concept problems (priming) or compared worked solutions across one of four different analogical reasoning conditions. These four conditions varied according to the type of examples compared (single-concept vs. synthesis) and structural...

We derive mathematically a class of metrics for signals and images, considered as elements of R , that are based upon the structural similarity (SSIM) index. The important feature of our construction is that we consider the two terms of the SSIM index, which are normally multiplied together to produce a scalar, as components of an ordered pair. Each of these terms is then used to produce a norm...

In studies of analogical reasoning, the distinction between surface and structural similarity has been repeatedly investigated. However, this distinction has not been investigated in a generative analogy where target representations are not provided in advance. This study uses computational methods to analyze how this distinction is involved in generative analogy. In the experiment, participant...