![](bg4.png)
dimension values distinguish the sub-concepts: “nursery” and “kindergarten”. The
dimension can only occur on sister concepts and a given value can only appear on one
of these sister concepts. In this way, a concept must be distinguished from each of its
nearest super-ordinate concepts as well as from each of its sister concepts by at least
one feature specification [5]. These principles enable us to generate well-structured
feature sets that are assumed to be useful for the feature-based similarity
computations. Tables 1 and 2 show examples of the expressed feature structures.
Table 1. Example of german data source (terms and feature sets).
ID Term Feature-values
G2 preschool education {ISCED97, children & young, ISCED0}
G5 kindergärten {ISCED97, children & young, ISCED0, child welfare, 3-6y.o.}
G7 schulkindergärten & vorklassen {ISCED97, children & young, ISCED0, preparation}
G10 primary education {ISCED97, children & young, ISCED1}
G11 primary school {ISCED97, children & young, ISCED1, <6-10y.o.<}
G13 secondary education { ISCED97, children & young, ISCED2+3}
G14 lower secondary level {ISCED97, children & young, ISCED2+3, <10-16y.o.<}
G15 school offering one single course {ISCED97, children & young, ISCED2+3, <10-16y.o.< , single}
G16 hauptschule {ISCED97, children & young, ISCED2+3, <10-16y.o.< , single , general basic, 5-9
th
grade}
G18 gymnasium {ISCED97, children & young, ISCED2+3, <10-16y.o.< , single, intensified, 5-12/13
th
grade}
G19 schools offering several courses {ISCED97, children & young, ISCED2+3, <10-16y.o.< , several}
Table 2. Example of danish data source (terms and feature sets).
ID Term Feature-values
D2 pre primary {ISCED97, children & young, ISCED0}
D4 kindergarten {ISCED97, children & young, ISCED0, 3-6y.o.}
D6 single structure {ISCED97, children & young, ISCED1+2}
D7 alternative structure {ISCED97, children & young, ISCED1+2, alternative}
D8 home tuition { ISCED97, children & young, ISCED1+2, alternative, compulsory, 6-16y.o}
D9 efterskole or youth school {ISCED97, children & young, ISCED1+2, alternative, compulsory, <14-18y.o.<}
D10 efterskole {ISCED97, children & young, ISCED1+2, alternative, compulsory, <14-18y.o.<, boarding school, approved
by state}
D11 youth school {ISCED97, children & young, ISCED1+2, alternative, compulsory, <14-18y.o.<, day-to-day, public
municipal council}
D14 municipal school {ISCED97, children & young, ISCED1+2, formal teaching, municipality}
D16 0-9
th
form {ISCED97, children & young, ISCED1+2, compulsory}
D17 0
th
form {ISCED97, children & young, ISCED1+2, compulsory, preparation}
D18 1-9
th
form {ISCED97, children & young, ISCED1+2, compulsory, general basic}
D19 10
th
form {ISCED97, children & young, ISCED1+2, optional}
Creation of Feature-term Matrices: In order to compute similarities, matrices
referring to the German- and Danish educational systems which, respectively, consist
of 58 and 52 terms are manually generated from the feature sets. Feature value
columns are defined in the following way:
1. All feature values existing in the Danish and German data sources are registered in
both matrices.
2. If feature values in the Danish and German matrices are completely overlapping
(e.g. “ISCED0-pre-primary” in DK and “ISCED0-pre-primary” in GE), the feature
columns in question should be merged into one column.
3. If a feature is possessed by a term, the numeric value should be “1”, otherwise “0”
in the matrices.
4. If a feature value in one matrix is completely included in a feature value in the
other matrix (e.g. “ISCED1+2” in DK and “ISCED1” in GE), a term possessing the
feature that includes the other feature (e.g. Danish “ISCED1+2”) should have numeric
value “1” in both feature columns (e.g. “ISCED1+2” in DK and “ISCED1” in GE). It
means that a term possessing a feature value that is included in the other feature (e.g.
37