Researchers have been interested recently in publishing and linking Humanities datasets following Linked Data principles. This has given rise to some issues that complicate the semantic modelling, comparison, combination and longitudinal analysis of these datasets. In this research proposal we discuss three of these issues: representation round- tripping, concept drift, and contextual knowledge. We advocate an inte- grated approach to solve them, and present some preliminary results.
15. (2)
Concept
Dria
• Models drift over time
• Classes merge, split, change their properties
(beroepklassen)
• Although, some core meaning remains
(shoemakers)
• Can we automatically identify and align drifted
concepts? With what vocabulary/semantics?
? ?
t1 t2 tn
18. (3)
Contextual
Knowledge
Shoemaker
Shoemaker
Amsterdam
Leiden
1889
1971
Vrowen
Women
+
Men
Works
with
leather
Businessman
Schoemakers
19. (3)
Contextual
Knowledge
Shoemaker
Shoemaker
Amsterdam
Leiden
1889
1971
Vrowen
Women
+
Men
Works
with
leather
Businessman
Schoemakers
20. Evalua&on
• Exis&ng
(classical)
research
results
on
Humani&es
datasets
• We
use
them
as
gold
standards
• Itera&ve
refinement
process
21. Research
Ques&ons
We
aim
at
providing
algorithms,
formalisms
and
tools
to
disambiguate,
clean,
prepare,
normalize,
transform,
link
and
query
Humani&es
datasets,
conforming
a
framework
for
effec&ve
Humani&es
data
publishing
in
the
Seman&c
Web.
• Can
RDF
data
models
faithfully
represent
Humani&es
datasets?
Is
an
RDF-‐based
format
round-‐tripping
framework
possible?
• How
can
we
model
concept
dria?
Can
driaed
concepts
be
aligned?
• Can
we
infer
dynamic
concept
defini&ons
from
explicitly
formalized
contexts?
Can
these
contexts
help
solving
concept
dria?