Search results

1

Evaluation of Selected Approaches to Clustering Categorical Variables

100%

Šulc Z.

Statistics in Transition new series

|

2014

|

vol. 15

|

issue 4

591–610

EN

This paper focuses on recently proposed similarity measures and their performance in categorical variable clustering. It compares clustering results using three recently developed similarity measures (IOF, OF and Lin measures) with results obtained using two association measures for nominal variables (Cramér’s V and the uncertainty coefficient) and with the simple matching coefficient (the overlap measure). To eliminate the influence of a particular linkage method on the structure of final clusters, three linkage methods are examined (complete, single, average). The created groups (clusters) of variables can be considered as the basis for dimensionality reduction, e.g. by choosing one of the variables from a given group as a representative for the whole group. The quality of resulting clusters is evaluated by the within-cluster variability, expressed by the WCM coefficient, and by dendrogram analysis. The examined similarity measures are compared and evaluated using two real data sets from a social survey.

2

Využití korpusových metod v popisu češtiny: příklad kolostrukční analýzy

51%

Lehečková E.

Časopis pro moderní filologii (Journal for Modern Philology)

|

2017

|

vol. 99

|

issue 2

167-180

EN

The paper presents a review of principles and applicability of collostructional analysis — a cluster of corpus methods developed by Anatol Stefanowitsch and Stefan Th. Gries since 2003. Collostructional analysis measures the strength of association by which lexemes are attracted to a particular position in a construction. It derives from the Construction Grammar concept of construction as conventionalized pairing of form and meaning. Collostructional analysis allows for systematic measurements of the degree of conventionalization of constructions. The paper introduces various types of collostructional analysis and provides an overview of research areas where collostructional analysis has been employed. It concludes with a case showing how collostructional analysis can be applied to the description of Czech.

3

Kolokační grafy a sítě s použitím nástroje #LancsBox: aplikace v angličtině a češtině

45%

Václav B., Pořízka P.

Časopis pro moderní filologii (Journal for Modern Philology)

|

2021

|

vol. 103

|

issue 1

36-59

XX

This article deals with the notion of collocation graphs and lexical networks, which not only represent the visualization of the collocational relationship between linguistic units — these have been traditionally displayed in a tabular form with frequency distributions and association measure values — but also an important analytical method in its own right. We illustrate the use of collocation graphs and networks with two case studies as examples demonstrating the use of this technique in lexicography and discourse analysis. The examples are based on both English and Czech corpora, which we analysed using #LancsBox, a free tool which can build collocation graphs and networks on the fly.

Refine search results

2 Časopis pro moderní filologii (Journal for Modern Philology)

1 Statistics in Transition new series

1 Lehečková E.

1 Pořízka P.

1 Václav B.

1 Šulc Z.

1 2021

1 2017

1 2014

Evaluation of Selected Approaches to Clustering Categorical Variables

Využití korpusových metod v popisu češtiny: příklad kolostrukční analýzy

Kolokační grafy a sítě s použitím nástroje #LancsBox: aplikace v angličtině a češtině