Re: When to use has_broader_match?

Antoine wrote:
> 2. Maybe Michael would be interested to read the parts
> on SKOS and OWL in the paper I cited in the other
> thread [2]
> [2] https://doi.org/10.1016/j.websem.2013.05.001

The relevant section of that paper is "4.4 Mapping relations".

Michael wrote:
> But I don't get has_broader_match or
> has_narrower_match. If one entity is broader or
> narrower than the other (which I interpret as
> super-class or super-part relations) then I don't
> understand how they can also be matches. Similarly for
> has_related_match.

When the W3C working group that published SKOS discussed this issue, it
acknowledged that large parts of the KOS community saw inter-KOS "mapping"
relations and intra-KOS "semantic" relations as distinct, even disjoint.

Making this distinction in SKOS, however, would have required a way to
formally "contain" a concept scheme -- along with its semantic relations --
as something distinct and separate from other concept schemes.

SKOS was however designed to support a more fluid and dynamic sense of
concept scheme -- as something that could evolve over time through
aggregation or division, through including concepts from multiple
namespaces, or through overlapping with other concept schemes. Any notion
of making "mapping" relations formally disjoint from "semantic" relations
was therefore off the table.

Basically, the working group could see no basis for distinguishing
"mapping" from "semantic" relations, so it fell back on admitting that the
difference between the two was not formal in nature, but "conventional"
(ie, nothing would actually break, in a formal sense, if a mapping were
expressed with skos:broader instead of skos:broaderMatch, so splitting one
concept scheme into two would not break those relations).

Oops - I see that Antoine made the same point on another thread but will
send this off anyway...

Michael wrote:
> Also, to use SKOS and not fall into OWL Full, I
> need to pun every class I want to assert a SKOS object
> property on.

I'd be interested to hear more about what you mean by "pun every class". It
does not formally contradict the SKOS data model if a SKOS concept is also
declared to be an OWL class, and I do not see how the reverse could be a
problem. According to the SKOS data model (which is itself expressed in
OWL), there are only two things in the formal semantic universe that cannot
be asserted to be SKOS Concepts: SKOS Collections and SKOS Concept Schemes.
There are even vocabularies where terms are declared to be both OWL
properties and SKOS concepts - see, for example,
https://id.loc.gov/vocabulary/relators/act.html .

Michael wrote:
> I think I also get has_related. When two Concepts are
> related (most likely in OWL by some property other than
> has_Sub_Part). E.g., if Fido was an instance of the Dog
> class and Michael has_Pet Fido then we could say that
> Michael has_related Fido (and vice versa since
> has_related is symmetric).

skos:related is kinda like dcterms:relation or rdfs:seeAlso, only with
skos:Concept as domain and range. The SKOS "mapping properties" support
more specific types of relation.

> And has_close_match would indicate that two entities in
> OWL are (probably) the same entity. If they are
> individuals then they are owl:sameAs and if class or
> properties owl:equivalentTo each other.

Not quite. skos:exactMatch is closer to the notion that the entities are
the same because it is transitive, where skos:closeMatch is not.

> Also, what about OWL properties?. I'm assuming in this
> context has_broader means the broader property is a
> super-property of the other property, is that correct?
> Also, of course I would need to pun properties as well.

I'm not following... The other property would be rdfs:subPropertyOf
skos:broader?

Christophe wrote:
> "Broader" means if one (human) is interested by the
> Broader, (s)he will be interested by this too.

Another way to put it is that SKOS is designed more as a basis for query
expansion than for inferencing.

Dean Allemang made a fascinating experiment in "expressing Chebi in SKOS"
(Semantic Web for the Working Ontologist, Second Edition, Chapter 13). When
using SKOS in place of OWL, he concluded that "the representation is
simpler but the query is more complex ... a common trade-off in
representation -- does the model do more work, with a more involved
representation, or does the query do more work?"

Christophe wrote:
> In today's world of AI digesting and classifying using
> statistics rather than scientific models and cartesian
> reasoning, SKOS looks like paddling against the tide
> but... who knows !

If you assume that the value of SKOS should lie in formal representation
and reasoning, then sure. But each SKOS concept has its own word cloud of
labels (in the case of AGROVOC, in up to 25 languages), and SKOS be used to
train machine learning engines, eg to use with tools such as TensorFlow
(see the excellent annif.org). By your reasoning, might one argue that OWL,
which models the world in terms of mathematical sets, is even more like
paddling against that tide?

Tom

On Fri, Jan 6, 2023 at 7:30 AM Antoine Isaac <aisaac@few.vu.nl> wrote:

> Hello Michael, Christophe,
>
> As a complement to what Christophe says (excellent move to have tried
> ChatGPT on this ;-) )
>
> 1. broadMatch, narrowMatch and relatedMatch may be especially useful to
> link different concept schemes, when there is no exact mapping or close
> mapping between two concepts of these schemes. See the example with
> ex1:referenceAnimalScheme and ex2:eggLayingAnimals at [1]. This is quite a
> made-up and extreme example, but hopefully it illustrates how two concepts
> schemes that one may want to map, may have very different semantic grain.
>
> 2. Maybe Michael would be interested to read the parts on SKOS and OWL in
> the paper I cited in the other thread [2]
>
> Cheers, (and Happy New Year!)
>
> Antoine
>
> [1] https://www.w3.org/TR/skos-primer/#secmapping
> [2] https://doi.org/10.1016/j.websem.2013.05.001
>
>
> On 29/12/2022 12:07, Christophe Dupriez wrote:
> > Hi Michael and welcome in SKOS wonderland !
> >
> > The list will object if I am wrong. For me, SKOS is about "human made
> for human" classification systems. "Broader" means if one (human) is
> interested by the Broader, (s)he will be interested by this too.
> >
> > The "match" properties are essentially used to correlate different
> classification systems. "Broader_Match" means if one (human) is interested
> by the Broader_Match in (another) classification system, (s)he MAY be
> interested by this too.
> >
> > In today's world of AI digesting and classifying using statistics rather
> than scientific models and cartesian reasoning, SKOS looks like paddling
> against the tide but... who knows !
> >
> > Happy New Year, it will be an interesting one !
> >
> > Christophe
> >
> > P.S. This is what ChatGPT has to say on the topic:
> >
> > dupriez@destin.be
> > How would you explain the similarities and the differences between two
> properties of the SKOS standard: "Broader" and "Broader_Match" ?
> >
> > SKOS (Simple Knowledge Organization System) is a standard for
> representing thesauri, classification schemes, and other types of
> controlled vocabulary as a set of concepts, and the relationships between
> those concepts.
> >
> > The "broader" property is a relationship between two concepts in a SKOS
> vocabulary, where the concept on which the property is applied (the
> "narrower concept") is a more specific concept within the hierarchy of the
> vocabulary, and the concept that is the value of the property (the "broader
> concept") is a more general concept. This relationship indicates that the
> narrower concept is a subclass or subcategory of the broader concept.
> >
> > For example, in a vocabulary about animals, the concept "dog" might have
> the broader property with a value of "mammal," because dogs are a type of
> mammal.
> >
> > The "broader_match" property is similar to the "broader" property, but
> it is used to link a concept in one SKOS vocabulary to a broader concept in
> another SKOS vocabulary. This can be useful when two vocabularies are being
> used together, and there is a need to align the concepts in one vocabulary
> with the concepts in the other vocabulary.
> >
> > For example, if you are using a vocabulary about animals that includes
> the concept "dog," and you also want to use a vocabulary about pets that
> includes the concept "canine," you could use the "broader_match" property
> to link the "dog" concept in the animals vocabulary to the "canine" concept
> in the pets vocabulary. This would indicate that the "dog" concept is a
> more specific version of the "canine" concept, and that the two concepts
> are related.
> >
> > In summary, the "broader" property is used to relate concepts within a
> single SKOS vocabulary, while the "broader_match" property is used to
> relate a concept in one SKOS vocabulary to a broader concept in another
> SKOS vocabulary.
> >
> >
> > Le 28/12/22 à 20:57, Michael DeBellis a écrit :
> >> I'm an experience OWL developer but I'm just getting up to speed on
> SKOS. I think I understand the basics: that has_broader indicates a
> relation between two Concepts where the broader Concept (the object) is a
> superclass or super-part of the subject. E.g., Mammal has_broader Animal.
> Also, to use SKOS and not fall into OWL Full, I need to pun every class I
> want to assert a SKOS object property on.
> >>
> >> I think I also get has_related. When two Concepts are related (most
> likely in OWL by some property other than has_Sub_Part). E.g., if Fido was
> an instance of the Dog class and Michael has_Pet Fido then we could say
> that Michael has_related Fido (and vice versa since has_related is
> symmetric).
> >>
> >> And has_close_match would indicate that two entities in OWL are
> (probably) the same entity. If they are individuals then they are
> owl:sameAs and if class or properties owl:equivalentTo each other.
> >>
> >> So far so good (I think, please correct me if any of that is wrong).
> But I don't get has_broader_match or has_narrower_match. If one entity is
> broader or narrower than the other (which I interpret as super-class or
> super-part relations) then I don't understand how they can also be matches.
> Similarly for has_related_match.
> >>
> >> Also, what about OWL properties?. I'm assuming in this context
> has_broader means the broader property is a super-property of the other
> property, is that correct? Also, of course I would need to pun properties
> as well. Any feedback would be appreciated.
> >>
> >> Michael
> >> https://www.michaeldebellis.com/blog
> >
> >
> > --
> > Christophe Dupriez
> > DESTIN-Informatique.com
> > Projet AKUINO.net
> > Tél.: +32 475.77.62.11
> > Twitter @AkuinoNET
> >
>
>

-- 
Tom Baker <tom@tombaker.org>