Semantic search

Jump to navigation Jump to search

Annotating axioms in OWL - Reloaded

Yesterday I sent a lengthy mail to the OWL-ED Mailinglist] about how to annotate axioms. Peter Patel-Schneider himself, first author of the OWL Semantics specification, told me in nice words that my solution sucked heavily, by pointing out that the semantics of annotations in OWL are a tiny bit different than I thought. Actually, they are not at all as I thought. So, in the evening hours, instead of packing my stuff for a trip, I tried to solve the problem anew. Let's see where the problem will be this time.

Peter, you were right, I was wrong. I took a thorough look at the Semantics, and I had to learn that my understanding of annotations was totally screwed. I thought they would be like comments in C++ or Prolog, but instead they are rather like a second ABox over (almost) the whole universe. This surprised me a lot.

But still, I am not that good at giving up, and I think my solution pretty much works syntactically. Now we need only a proper Semantics to get a few things right.

What would be the problem? Let's make an example. I need some kind of Syntax to give axioms name. I will just take Name":" Axiom. This is no proposal for the Abstract Syntax extension, this is just for now.

Axiom1: SubClassOf(Human Mortal)
Axiom2: Individual(Socrates type(Human))

Do they entail the following?

Axiom3: Individual(Scorates type(Mortal))

Well, pitily they don't. Because the Axiom3 has a name, Axiom3, that is not entailed by Axiom1 and Axiom2. Their contents would be entailed, but the name of the axiom would not.

I guess, this is the problem Peter saw. So, can we solve it?

Well, yes, we can. But it's a bit tricky.

First, we need the notion of Combined Inverse Functional Properties, CIFP. A CIFP has several dimensions. A CIFP with dimension 1 ist a normal Inverse Functional Property. A CIFP with dimension 2 over the properties R, S can be represented with the following rule: a R c, a S d, b R c, b S d -> a = b. This means, in a two dimensional space I can identify an individual with the help of two roles. More on this here: http://lists.w3.org/Archives/Public/semantic-web/2005Feb/0095.html

Second, we extend the semantics of OWL. Every axiom entails reifying annotations. This means:

SubClassOf(Human Mortal)

entails

Individual(Statement1 type(rdf:statement)
annotation(rdf:subject Human)
annotation(rdf:property owl:SubClassOf)
annotation(rdf:object Mortal))

or, in N3:

Human owl:subClassOf Mortal.

entails

Statement1 rdf:type rdf:statement.
Statement1 rdf:subject Human.
Statement1 rdf:property owl:subClassOf.
Statement1 rdf:object Mortal.
rdf:subject rdf:type owl:AnnotationProperty.
rdf:predicate rdf:type owl:AnnotationProperty.
rdf:object rdf:type owl:AnnotationProperty.

Third, we have to state that we have a 3D-CIFP for statements over rdf:subject, rdf:property and rdf:object*. This is to ensure that Statement1 always maps to the same element in the universe, even though an OWL API could give it a blank node, or a different URI everytime (mind you, I am not suggesting to extend the OWL language with CIFPs, I just say that it is used here in order to state that all triples with the same subject, object and predicate actually is the same triple).

Fourth, the above statement also entails

Individual(Axiom1 type(owl11:axiom)
annotation(owl11:consistsOf Statement1))

or, in N3:

Axiom1 rdf:type owl11:axiom.
Axiom1 owl11:consistsOf Statement1.
owl11:consistsOf rdf:type owl:AnnotationProperty.

Fifth, owl11:consistsOf needs to be an n-dimensional CIFP with n being the number of triples the original axiom got translated to (in this case, happy us!, n=1).

This assures that an axiom is always the same, whatever it's name is, as long as it expresses the same thing. Thus, in our example, Axiom3 would indeed be entailed by Axiom1 and Axiom2. So, even if two editors load an ontology an annotate an axiom, they could later interchange and find each others annotation attached to the correct axiom.

This is only a rough sketch of the way, and yes, I see that the Interpretation gets filled up with a lot of annotations, but I still think that this is quite easy to implement, actually. Both the OWL API by Bechhofer and Volz and the KAON2 API by Motik offer access to axioms on an ontology level, and also offer the possibility to check if they are the same anyway, if I remember correctly (which is basically a shortcut for the whole semantic entailment and CIFP-stuff proposed earlier). All they need is a further field containing the URI of the axiom.

As said, this looks far more nasty than it actually is, and for most practical reasons it won't do much harm. Now we finally can annotate axioms, yeeeha!

Merrily awaiting Peter to acknowledge that this is a brilliant solution :) Or else tell me I did it all wrong again, so that I have to think over the weekend how to solve this problem again.

Cheers, denny

 *What I mean with that is the following rule: a=b :- a rdf:subject s, a rdf:property p, a rdf:object o, b rdf:subject s, b rdf:property p, b rdf:object o

Another Semantic MediaWiki

I stumbled about another Semantic MediaWiki, an implementation created by Hideaki Takeda and Muljadi Hendry of the Japanese National Institute of Informatics in Tokyo. Their implementation looks very neat, although it is quite different in a few basic things (that we consider crucial in order to work), take a look at their full paper (it's in their wiki - oh, and it's in Japanese).

The basic difference between their approach and the one we suggest is that they add metadata management abilities to MediaWiki - which is cool. But they don't seem to aim at a full integration into the Wikipedia, i.e. embedding the metadata into the article text instead of appending it at some place. Actually, if we had software that is able to process natural languages, we wouldn't need our approach, but their would still be useful.

Nevertheless, they have a big huge advantage: a running system. Go there, take a look, it's cool! Actually, we have a system online too, but won't yet disclose the link due to a bug that's a kind of showstopper. But expect it to be online next week - including the source and all! It will be just a first version, but I sure hope to gather the people who want to work on it around the code.

Ante Vrandečić (1919-1944)

I knew that my father was named for his uncle. His other brother told me about him, and he was telling me that he became a prisoner of war and that they lost his trace. Back then, I didn't dare to ask on which side he was fighting, and when I would have dared to ask, it was too late.

Today, thanks to the increasing digitalisation of older sources and their publication on the Web and the Web being indexed, I accidentally stumbled upon a record about him in a three thousand pages long book, Volume 8 of the "Victims of the War 1941-1945" (Žrtve rata 1941-1945).

He was a soldier in the NOV i POJ (Yugoslav partisans), became a prisoner of war, and was killed by Germans during a transport in 1944. I don't know where he was captured, from where to where he was transported, where he was killed.

My father, his namesake, then moved to Germany in the 1970s, where he and my mother built a new life for themselves and their children, and where I was born.

I have a lot of complicated emotions and thoughts.

Apricot ist keine Farbe

Zumindest nicht für Männer. Es gibt aber einen kleinen Anteil Frauen, die vier statt drei verschiedene Zapfen im Auge haben. Dadurch können sie tatsächlich mehr verschiedene Farben sehen (bis zu 100 Millionen verschiedene Farben -- statt nur eine Million bei uns Männern, und den meisten Frauen, nur etwa 2-3% der Frauen sind sogenannte Tetrachromanten). Es sei unvorstellbar, wie das aussehe (ja, das kann ich mir vorstellen, ich meine, nicht vorstellen).

Blöd. Ich fühle mich jetzt voll benachteiligt. Gott ist doch Sexist, verflixtnochmal.

Aprilscherz

Die Meldung vom 1. April war leider nur ein Aprilscherz. Zur Zeit sind leider kaum Updates zu erwarten: ab Freitag bin ich für eine Woche weg, und zuvor will ich soviel wie möglich für meine Diplomarbeit erledigen. Aber ich bastel schon an einem größeren Umbau an Nodix - doch wird er nicht vor Mai oder Juni vollzogen werden, tut mir leid. Danke jedenfalls für euer Verständnis!

Architecture for a multilingual Wikipedia

I published a paper today:

"Architecture for a multilingual Wikipedia"

I have been working on this for more than half a decade, and I am very happy to have it finally published. The paper is a working paper and comments are very welcome.

Abstract:

Wikipedia’s vision is a world in which everyone can share in the sum of all knowledge. In its first two decades, this vision has been very unevenly achieved. One of the largest hindrances is the sheer number of languages Wikipedia needs to cover in order to achieve that goal. We argue that we need anew approach to tackle this problem more effectively, a multilingual Wikipedia where content can be shared between language editions. This paper proposes an architecture for a system that fulfills this goal. It separates the goal in two parts: creating and maintaining content in an abstract notation within a project called Abstract Wikipedia, and creating an infrastructure called Wikilambda that can translate this notation to natural language. Both parts are fully owned and maintained by the community, as is the integration of the results in the existing Wikipedia editions. This architecture will make more encyclopedic content available to more people in their own language, and at the same time allow more people to contribute knowledge and reach more people with their contributions, no matter what their respective language backgrounds. Additionally, Wikilambda will unlock a new type of knowledge asset people can share in through the Wikimedia projects, functions, which will vastly expand what people can do with knowledge from Wikimedia, and provide a new venue to collaborate and to engage the creativity of contributors from all around the world. These two projects will considerably expand the capabilities of the Wikimedia platform to enable every single human being to freely share in the sum of all knowledge.

Architektur

Die bisherige Version des DSA4 Werkzeugs ist in C++ programmiert. Für die Daten entschied ich mich damals für ein XML-Datenformat, was zu der Anbindung von Xerces führte. Die GUI wurde mit wxWindows gemacht (die ersten Versionen, falls sich noch jemand erinnert, beruhten auf MSXML und native Windows GUI Elementen). Der Wechsel auf Xerces und wxWindows wurde durchgeführt, um Plattformunabhängig zu sein. Und tatsächlich: der Code compilierte auch unter Linux (dank hier an die Portierer). Aber richtig laufen tat er nie, es waren immer irgendwelche Bugs in der Linuxversion, die ich nicht in der Windowsversion nachvollziehen konnte.

Außerdem war das verwendete C++ viel zu kompliziert. Ich benutzte massig Templates (vor allem für die Rassen, Kulturen und Professionen), was den Code sehr schwer lesbar und bearbeitbar machte. Auch ein schlichtes compilen war eine recht anspruchsvolle Prozedur. Ich gehe davon aus, dass deswegen nie im größeren Maße Entwicklungsarbeit von anderen als von mir geleistet wurde: mein Code war schlicht zu kompliziert. Aus de selben Grund habe ich selber ja in den letzten Monaten den Code nicht angefasst.

Dies ist die wichtigste Lektion für die neue Version: deutlich einfacherer Code. Änderungen müssen auch ohne sich extrem reinzuarbeiten möglich sein. Idealerweise sollte das ganze Werkzeug interpretiert sein. Kein compilen mehr. Ändern. Neustart. Fertig.

Wie ich das erreichen will verrate ich in den nächsten Blogeinträgen genauer (deswegen habe ich auch nicht so viel geschrieben die letzten Tage -- und weil ich auf Dienstreisen in Kaiserslautern und Düsseldorf war -- ich wollte zunächst ein halbwegs tragbares Konzept haben. Das kommt jetzt die nächsten paar Tage. Hier schonmal eine grobe Übersicht -- ich werde im Folgenden genauer auf die Begriffe und den Aufbau eingehen.

Mozilla, die Open Source Gruppe die uns nicht nur Firefox und Thunderbird beschert hat, hat, was die Basis ihrer Tools ist, ein umfangreiches, sogenanntes Mozilla Application Framework erstellt. Im Großen und Ganzen ist es ein supermächtiges Biest -- ich will es soweit zähmen, damit das DSA4 Werkzeug darauf läuft. Hierbei gibt es eine Hauptengine, die XULRunner heißt. XUL ist so etwas wie HTML, bloß für GUIs von Anwendungen (und man kann tatsächlich auch HTML und JavaScript in XUL mit benutzen). Das bedeutet, das User Interface des neuen DSA4 Werkzeugs zu ändern wird so leicht sein wie HTML-Seiten schreiben, ja, sogar mit CSS arbeitet das ganze zusammen. Interessant ist hierbei vor allem das Verwenden von JavaScript, das eine dynamische GUI erlaubt. Die Applikationslogik hingegen kann entweder in JavaScript implementiert werden, oder auch in C++ oder Java (oder Python), um dann über XPCOM (oder PyXPCOM) darauf zuzugreifen. Potenziell also kann man auch Teile des bisherigen Codes wiederverwenden! Schließlich, die Daten werden in RDF gespeichert, einer XML-basierten Sprache, die aber deutlich Vorteile zu XML (und ein paar Nachteile) aufweist.

All dies unterstützt das Mozilla Application Framework von Haus aus. Anhand von Thunderbird und Firefox sieht man ja, dass das durchaus zu brauchbaren Applikationen führen kann. Ich hoffe, dass es auch hier aufgeht.

Asterix in Gefahr

Dieser Tage erschien der 33. Band der Asterix-Reihe: Gallien in Gefahr. Nein, kein "Asterix rettet Gallien", oder "Asterix bringt Gallien in Gefahr", oder ähnlich, sondern schlicht der reißerische Titel "Gallien in Gefahr". Im französischen heißt der Band Le ciel lui tombe sur la tête, Der Himmel fällt ihnen auf den Kopf, aber bei Asterix waren die Übersetzungen schon immer sehr frei - und meistens dadurch auch herausragend gut! (Ich bin, mein lieber Freund, sehr glücklich, dich zu sehn!" - "Das ist ein Alexandriner." -Asterix und Kleopatra). Vor dem weiterlesen ist es vielleicht sinnvoll, den Band zuerst zu lesen, sonst wird einiges vorweggenommen. Ich verrate zwar nicht, wer stirbt, aber dennoch.

Aber kommen wir zum Inhalt. Überraschend wenig gelacht. Ich muss mal die alten Hefte rauskramen, ob man da auch so wenig gelacht hat, ob man nur die besten Stellen sich gemerkt hat (mein Liebling ist Asterix als Legionär, und da habe ich reichlich gelacht, da bin ich mir sicher). Asterix war immer dafür begann, mit seiner Zeit zu spielen. Das Jahr 50 v. Chr. Ganz Gallien ist von Römern besetzt... Das zeigte einen gewissen Rahmen auf, auch wenn er schon in Vergangenheit arg gestreckt wurde: Die große Überfahrt führte nach Amerika, Asterix im Morgenland nach Indien. Doch diesmal reist Asterix gar nicht, sondern vielmehr kommt die Fremde in das kleine gallische Dorf. Und zwar heftig.

Aliens besuchen das kleine gallische Dorf. Ihr Kampf gegen die Römer hat Gerüchte um ihre letale Geheimwaffe ins ganze Universum verbreitet. Die guten Aliens kommen zuerst, um Asterix zu warnen, und dann kommen die bösen nach, und es kommt zu einer Schlacht zwischen den Außerirdischen. Gewaltig große Bilder, oft eine halbe Seite, ein Panel gar die ganze Seite bedeckend - ungewöhnlich für Asterix.

Man mag den Band befremdlich finden. Aber so schlecht ist er nicht. Es ist zudem nicht schwer durch die oberflächliche Geschichte zu stoßen, zu sehen, was dahinter steckt: das gute Alien ist offensichtlich Micky Maus ohne Ohren, ja, selbst der Name des Planeten von dem sie stammen ist ein Angram auf Walt Disney. Sogar die Details - Tuuns Knöpfe, die Handschuhe, die Gesichtsmimik - stimmen. Und er isst Heißen Hund - deutliche Anspielung auf Amerika. Sein Begleiter, im Stile Schwarzeneggers, eine Mischung aus Terminator und Superman, hingegen ist ein Klon, ein Superheld, austauschbar durch den anderen. Dies sind die Ikonen des Amerikanischen Comics. Ich frage mich nur, was der Name Tuun und seines weisen Mannes Hubs bedeutet?

Die bösen Aliens hingegen stammen vom Planeten Nagma, ebenfalls ein nichts verhehlendes Anagram auf japanische Comics. Auch sind sie so insektenhaft gezeichnet und bewegen und kämpfen, wie man es von machem Manga gewohnt ist. Ihr deutsch, oder vielmehr gallo-römisch, ist schlecht, und die Amerikaner, entschuldigung, die guten Aliens behaupten, dass sie nur alle ihre Erfolgsrezepte kopieren. Das erste, was der Abgesandte der Nagmas macht, als er Asterix entgegentritt, ist es, ihm einen Friedensabkommen anzubieten, doch Asterix begrüßt den Außerirdischen mit Dresche. Und so kommt es zur Schlacht.

Amerikanische Superheldencomics, Walt Disneys Massenproduktion und Mangas überfluten den europäischen Markt, bedrängen die französisch-belgischen Künstler, wollen sich das Geheimnis ihres Zaubertranks aneignen wollen, das Geheimnis ihres Erfolgs. Das hätte man für die Nachricht dieses Bandes halten können. Uderzos Postscriptum zu seiner und Goscinnys Asterix-Reihe, der wahrscheinlich letzte Band des nunmehr 78-jährigen Uderzo. Sein Kommentar zur Geschichte des europäischen und globalen Comics.

Doch nach zwei Dritteln des Bandes fragt man sich, was will er nun sagen? Es wird kreuz und quer Frieden geschlossen und aufeinander geprügelt, die Römer und Piraten kriegen einen Gastauftritt, der wirkt, als ob man die Todo-Sachen der Liste "Was alles in einen Asterix-Comic auftauchen muss" noch abhandeln müsste, und am Ende wird allen das Gedächtnis gelöscht, so dass die Geschichte vollkommen folgenlos bleibt. Uderzo hätte viel sagen können, und man hätte zugehört. So aber deutete er einen Kommentar an, um dann doch nur irgendwie die Geschichte zum Ende zu bringen, bevor Seite 48 erreicht wird. Schade. Und warum sieht der römische Offizier diesmal wie Signore Berlusconi aus?

Sicher nicht der schlechteste Asterix. Wahrscheinlich der ungewöhnlichste.

At Wikimania 2006

I am here in Boston now, walking the sacred grounds of Harvard and MIT, and listening and talking with the great people who created the MediaWiki software that runs Wikipedia. At Thursday, Markus and I will host the Semantic Wikipedia panel, where we present the state of our implementation, and talk about how to make it real. We also have a tutorial on Sunday, about how to reuse knowledge from a Semantic MediaWiki.

If you're around Boston, MIT, Harvard, or if you even attend Wikimania and the Hacking Days, and want to meet -- contact me!


Comments are still missing on this post.

Auch das Internet hat ein Ende

Und zwar hier.

Auswärts bloggen

Es funktionier wirklich. Ich schreibe hier meinen ersten Blog-Eintrag von "nicht daheim".

Übrigens bin ich immer überrascht, wie manche Leute denken. Das erkennt man an so Kleinigkeiten wie meinem Handymenü. Wenn ich es auf lautlos stelle, dann deaktiviere ich nicht etwa das Klingeln, sondern aktiviere vielmehr die Stille.
Eigentlich, ein sehr schöner Gedanke. Manchmal sollten wir alle ein wenig Stille aktivieren.

Vor allem im Kino.

Auto hat 10000

Nachdem ich diesen Sommer 10.000 geworden bin (Tage), hat es mein Autole heute auch geschafft (Kilometer).

Hier fehlt noch ein Bild.

Babel

Strong recommendation for "Babel" by R.F. Kuang. It's a speculative fiction story set in 1830s Oxford with an, as far as I can tell, novel premise: one can cast spells (although they don't call it spells but it's just science in this world) by using two words that translate into each other, and the semantic difference between the two words - because no translation is perfect - is the effect of the spell. But the effect can only be achieved if you have a speaker who's fluent enough in both languages to have a native understanding of the difference.

One example would be the French parcelle and the English parcel, both meaning package, but the French still carries some of the former "to split into parts", with the effect that packages are lighter and easier to transport for the Royal Mail.

The story remains comfortable for the first half of the volume, with beautiful world building, character drawing, and the tranquil academic life of Oxford students, but then it suddenly picks up speed, and we can experience the events unfold with a merciless speed. The end is just in the right place, and it leaves me to yearn to revisit this world and the desire to learn what happened next.

The volume discusses some heavy topics - colonialism, dependency on technology, fairness, what is allowed in a revolution, the "neutrality" of science - and while we are still in the first half of the volume, it feels very on the nose, very theoretical - but that changes dramatically as we swing into the second half of the volume, and suddenly all these theoretical discussions become very immediate. Which does remind me of student life, where discussions about different political systems and abstract notions of justice are just as prevalent and as consequence-free as they seem to be here, at first.

The book was recommended by the Lingthusiasm podcast, which is how I found it.

I came for the linguistic premise, but I stayed for the characters and their fates in a colonial world.

Back again!

"Ein wenig Schmerz hat noch keinem weh getan"

Ich bin wieder zurück! Noch bin ich beim eMail-Beantworten, beim Überblick-verschaffen, beim in-neue-Lebenssituation-eingewöhnen und so fort. Schon bald gibt es mehr.
Danke jetzt schon für eure unglaubliche Treue! Ihr seid unglaublich!

Bad Santa

Brrrr... eiskalt hier im Lande.
Nettes Detail am Rande: wegen eines Problems mit einem Mailserver kam ich tatsächlich noch vor einer von mir verschickten eMail wieder in Deutschland an. Ts, moderne Technik halt... Ach ja, aus der Reihe Filme in 50 Worten

Billy Bob Thornton spielt einen äußerst heruntergekommenen Weihnachtsmann. Er trinkt, säuft, vögelt, klaut und benutzt vor Kindern schlimme Wörter. Und dann trifft er eine hübsche Frau, die noch an den Weihnachtsmann glaubt, und er ändert sich...

...kein bisschen.
Ein Film, der angenehmerweise bis zum Ende durchgehend böse bleibt und nicht irgendwann in friedliches Weihnachtstrallala übergeht -- anschauen, anschauen, anschauen!

Barcelona II

Wieder in Barcelona. Nachdem letztes Mal im November so ein Traumwetter war, war ich diesmal leicht gekleidet losgeflogen - und prompt ist es kälter als im Ländle. Würde mich nicht überraschen, wenn ich eine Erkältung mitschleppe...

Aber dafür habe ich diesmal sogar etwas Zeit, mir die Stadt anschauen. Wahnsinnggemütliche kleine Bars wie die Eclectica, supertolle Restaurants wie die Muscleria, etc. Die letzten zwei Tage war ich mit Barcelonesen unterwegs, heute mit Kai, einem Erasmusstudenten, und seiner Schwester Rosa. Spannend, wie die unterschiedlichen Einstellungen zu den Sehenswürdigkeiten der Stadt sind, was sie empfehlen, wo sie hingehen.

Die Stadt ist toll! Heute schaue ich noch die Sagrada Familia an, das freue ich mich besonders darauf. Und dann brauche ich ganz dringend Schlaf...

Beating the Second Law

Yihon Ding has an interesting blogpost taking analogies to the laws of thermodynamics and why this means trouble for the Semantic Web.

I disagree in one aspect: I think it is possible to invest the amount of human power to the system and to still keep it going. I can't nail it down exactly -- I didn't read "Programming the Universe" yet, so I can't really discuss it, but the feeling goes along the following lines: the value of a network increases superlinearly, if not even quadratic (Metcalfe's Law), whereas the amount of information increases sublinearly (due to redundancies in human knowledge). Or, put it in another way: get more people and Wikipedia or Linux gets better, because they have a constrained scope. The more you constrain the scope the more value is added by more people.

This is an oversimplification.

Berlin, Berlin, ich war jetzt in Berlin...

... und nicht in Olpe. Da fahre ich wohl in ein paar Wochen hin. Aber aus einem ganz anderen Grund. Dafür fliegt Schwesterchen nach Berlin. Aber auch aus einem ganz anderen Grund.

Und Berlin ist sehr wow. Der Reichstag, das Bundeskanzleramt, riesige, beeindruckende Gebäude; die gewaltigen Parks; atemberaubend: das Pergamonmuseum. Einfach unglaublich. Ich habe immer gedacht, der Pergamonaltar wäre halt ein Altar, also ein Steinblock. Niemand hat mir gesagt, dass sie den ganzen Tempel auseinandergeschnitten haben und nach Berlin gebracht haben! Unglaublich. Und dann geht man weiter, tritt durch einen Eingang, und denkt sich, hmm, irgendwie habe ich Blau im Nacken. Und da dreht man sich um, und ist gerade durch das Ischtartor getreten. Und es sieht noch viel beeindruckender aus, als in den Büchern. Ist halt auch etwas größer als in den Büchern.

Und Nofretete ist auch hübsch. Nicht ganz so hübsch wie Ginevra, also bleibt letztere mein Desktop-Hintergrund.

Und das Mauermusuem hat mich mehrfach auf meine Tränendrüse gedrückt. Wahnsinnsgeschichten. Und auf dem Weg zu einem allgemeinem Menschenrechtsmuseum. Mit Info zu Gandhi, zu dem Aufstand in Ungarn, zu den Religionen und ihren Gemeinsamkeiten, und vieles mehr. Aber halt auch: wie ist die Mauer gebaut? Die Helden, die Tunnel bauten. Die Helden, die trotz Befehl nicht auf die Flüchtlinge schossen. Die Helden, die den Stacheldraht hochheben, damit das Kind durchkommt. Die Helden, die stark genug waren, keine Gewalt anzuwenden. Ich weiß nicht, ob ich die selbe Stärke hätte.

Habe auch ein Stück Mauer gekauft. Und weggeschickt. Weil die Mauer muss weg.

Genau.

Ach ja, und die Arbeit war auch cool. Wahrscheinlich eine der coolsten Locations überhaupt: Unter den Linden 1. Direkt an der Museumsinsel.

Bescheidenheit

Don't be humble, you are not that great. - G. Meir

Besser spät als nie

Auch ich fang das Stöckchen. Wenn auch spät.

Warum bloggst du?

Weil ich manchmal glaube, etwas sagen zu können, das unterhält, nachdenken lässt, erinnert, berührt, zum lachen bringt, informiert, oder auch einfach nur die Zeit etwas angenehmer vorbeigehen lässt.

Seit wann bloggst du?

Nodix gibt es seit dem 15. Januar 2001. Das erste Mal, dass ich das ganze einen Blog nannte, und auch das Aussehen der Seite den üblichen Blogstandards anpasste, war erst am 21. August 2002, als die ersten 10000 Besucher zusammengekommen waren.

Selfportrait?

Eingebildet (glaubt, gut zu sein), verrückt (Arbeitet auch am Wochenende, und hat Spaß dabei), sich in Details verlierend (und dadurch nicht das tun, was er tun sollte), großspurig (die Menschheit retten wollen, und auch zu glauben, es zu können), dickköpfig (lässt sich schwer umüberzeugen), alles machen wollen (und auch von anderen das selbe verlangen), zu selten das Partizip benutzen (es sollte benutzend heißen), und Wikipedianer (behauptet zumindest die Wikipedia).

Ansonsten findet sich unter Denny eine bessere Beschreibung.

Warum lesen Deine Leser Deinen Blog?

Weil ich hin und wieder das schaffe, was ich in Punkt 1 schreibe. Außerdem schreibe ich so selten, dass die meisten Leser dafür nicht sonderlich viel Zeit brauchen.

Welche war die letzte Suchanfrage, über die jemand auf Deine Seite kam?

gutes karma

Das finde ich aber sehr erfreulich: sucht man bei Google.de nach gutem Karma, kommt man zu mir (Platz 3!)

Welcher Deiner Blogeinträge bekam zu Unrecht zu wenig Aufmerksamkeit?

Oh, ich dachte nicht dass Blogeinträge ein Recht auf Aufmerksamkeit haben. Aber wenn man mich so fragt... dass Männer schlauer als Frauen sind, wurde in diesem Blog schon behauptet, mit eben so viel Recht. Ansonsten schlägt auch das Risiko Alter in eine ähnliche Kerbe. Und dann bleibt noch mein liebster Blogeintrag, über das Pendeln.

Dein aktuelles Lieblings-Blog?

nakit-arts. Oh, ich meine be croative!. Da bleibe ich auf dem Laufenden, was daheim passiert, auch wenn ich nicht daheim bin.

An welche vier Blogs wirfst du das Stöckchen weiter und warum?

Uh, ich glaube, Blogger, die ich kenne, haben das Stöckchen schon gefangen. Ich werfe die jetzt einfach mal in die Luft, mal sehen, wer fängt! Linkt hierher, wenn ihr das Stöckchen gefangen habt!

Beyoncé's Number One in Country

Beyoncé very explicitly announced her latest album to be a country album, calling it "Cowboy Carter", and her single "Texas Hold 'Em" made her the first Black woman to top Billboard's Hot Country Songs charts.

It is good that Beyoncé made it so glaringly obvious that her song is a country song. The number of Black artists to have topped the Hot Country Song charts is surprisingly small: Charley Pride in the 70s, Ray Charles in a duet with Willie Nelson for one week in 1984, and then Darius Rucker and Kane Brown in the last decade or two.

Maybe one reason to understand why it is so hard to chart for Black artists in this particular genre: "Old Town Road", the debut single by Lil Nas X, first was listed on the Hot Country Song chart, but then Billboard decided that this was a mistake and instead recategorized the song, taking it off the Country charts in March 2019 before it would have become the Number One hit on April 6, 2019 were it not removed.

Billboard released a long explanation explaining that this decision had nothing to do with racism.

Cowboy Carter was released exactly in the same week five years after Old Town Road would have hit Number One.

I guess Beyoncé really wanted to make sure that everyone knows that her album and single are country.

Big Fish

aus der Reihe Filme in 50 Worten

Ein Vater hat die Angewohnheit, bei seinen Geschichten stets zu lügen. Alle lieben ihn dafür, bloß sein Sohn versucht, die Wahrheit über ihn herauszufinden, und begibt sich dabei auf eine Reise durch die Vergangenheit seines Vaters, die ihn erkennen lässt, dass nicht alles, was eine Lüge zu sein scheint, auch wirklich gelogen ist...

Es ist ein wunderschöner Film, der einen viel zu Lachen bringt, auch zum Nachdenken, und auch zum Lächeln (nicht jeder Film, der einen Lachen macht, bringt einen auch zum Lächeln). Der Film ist bunt, bilderfroh, skurill, genau so wie wir es von Tim Burton kennen und lieben.

Anschauen. Nicht verpassen. Unbedingt anschauen.

Black lives matter

Blick in die Kristallkugel

So, von hier aus einen guten Rutsch in das neue 2004!Wie überall üblich zu Jahresenden soll auch hier eine Vorschau stehen, wenn auch nur eine ganz kurze.Hierbei werde ich gar nicht über Nodix reden, da dieses selber ja bald Geburtstag feiert, und dafür ist das viel besser geeignet.

Da ich mindestens so gut wie 95% der Astrologen bin, werde ich also eine Vorschau auf 2004 wagen (eine Rückschau wäre zuviel Recherche - begnadet derjenige, der hierbei den Gag erkannt hat).

Dieses Jahr wird es, entgegen dem Trend, der sich fast bis an den Anfang des Jahrtausends zurückverfolgen lässt, keinen Herr der Ringe-Film geben.Alle Süchtigen müssen sich mit etwa einer Dreiviertelstunde neuer Szenen im Herbst begnügen, danach heißt es, sich auf drastische Entzugserscheinungen einzustellen.Als Metadon der Fantasyfans kann man die Realverflimung zum Letzten Einhorn betrachten, welches uns Ende des Jahres erfreuen sollte.Bedauerlicherweise erscheint der Film aber nicht rechtzeitig :( Dies wird frühestens im März bestätigt werden.
Die guten Nachrichten für alle Fantasyfans sind, dass der Herr der Ringe natürlich wieder Oscars einstreicht, zudem erreichen uns mehr Infos zur Verfilmung des Narniazyklus.

Auf Softwareseite ist Ultima X zu erwarten!Und zur allgemeinen Überraschung - bedenkt man, die Verschiebungsorgien von Ultima IX - erscheint es auch tatsächtlich 2004. Duke Nukem Forever hingegen erscheint nicht.

Die Amerikaner beweisen gegen Ende des Jahres, dass sie das Zählen geübt haben.Selbst Florida schafft es im ersten Anlauf, diese verantwortungsvolle Aufgabe zu meistern.Wiederholt werden die Angebote der Russen und Chinesen, Wahlbeobachter zu schicken, abgelehnt.

Aber solche allgemeinen Informationen interessieren eh Niemanden.Was wir einzig wissen wollen ist doch, was uns nächstes Jahr widerfährt.
Also, blicken wir tief in die Kristallkugel...
Das neue Jahr wird 366 Tage anbieten, die allesamt voller neuer Gelegenheiten sind.Die Tarotkarten verraten mir, dass wir jeden einzelnen Tag neue Fähigkeiten aneignen dürfen, interessanten Personen begegnen werden - wir müssen sie nur erkennen und ansprechen -, mit neuen Ideen jonglieren, und endlich dran gehen dürfen, lang gehegte Pläne in die Wirklichkeit umzusetzen.2004 ist die naheliegendste Möglichkeit, uns weiterzuentwickeln.
Auch 2004 werden wieder einzelne Rückschläge versuchen, uns zu entmutigen, aber wir sind als Einzige dafür verantwortlich, ob wir diese als Erfahrungen abbuchen wollen, oder uns durch diese Entmutigen lassen wollen.Die Sterne stehen günstig für die erste Möglichkeit.2004 beginnt mit der Sonne im Steinbock, einem ehrgeizigen Zeichen, das hoch hinaus will - was also sollte uns aufhalten, außer wir selbst?

Also, es wird ein spannendes Jahr.Ich hoffe Euch allen alles Beste, einen guten Rutsch und ein wunderschönes 2004!

Blogging from an E90

28 May 2008

After pondering it for far too long, I finally got a new mobile phone: a Nokia E90. It is pretty big and heavy, but I don't mind really. I am looking at it as a light-weight laptop replacement. But I am not sure I will learn to love the keyboard, really. Experimenting.

But since it has a full keyboard, programming in Python is indeed an option. I had Python on my previous phone too, but heck, T9 is not cool to type code.

Blumengruß

Ein neuer Donnerstag und eine neue nutkidz-Folge - natürlich passend zum morgigen Valentinstag! Für alle also, die es (fast) vergessen haben: pflückt Gänseblümchen! Vergesst nicht, Damen: wenn er euch keine Blumen schenkt, dann hasst er euch!
Ach ja, für alle Herren, denen gerade noch einfällt, dass sie doch jemanden lieben: bei Amazon kann man auch Blumen versenden. Frohen Valentinstag allen!

UPDATE
Ich schon wieder! Bin auch gleich wieder weg, wollte bloß die Veröffentlichung einer neuen Version des DSA4 Werkzeugs verkünden!

Bologna la dotta

Bologna ist großartig! Das erste Gebäude. das ich hier kennenlernte, war die Sala Borsa. Angekommen, im Hotel eingecheckt, spazieren, und sofort reinmarschiert. Man könnte es einen Mall nennen, aber mit einem sehr ausgewählten Angebot: zwei, drei Bibliotheken, Mediothek, Buchhandlungen, Studentenbedarf (Taschen, Blöcke), Internetcafé, WLAN-Access, Restaurants, unglaublich! Das ganze in einem wunderschänen, dezent renovierten alten Gebäude, das auf einer Ruine gebaut ist, wahrscheinlich aus römischer Zeit. Die Ruine kann man sehen, weil der Boden des Erdgeschosses aus Glas besteht, das ganze Gebäude ist eine große Halle, mehr oder weniger, mit mehreren Galerien, in der die ganzen tollen Geschäfte untergebracht sind.

Phantastischer Ort. Allein deshalb ist Bologna eine Reise wert. Ja, die Universität (gegründet 1088, damit die älteste Uni der Welt) ist auch ganz ansehnlich. Vorlesungen in diesen Hallen zu hören oder Prüfungen abzulegen in Renessaincegeschmückten Räumen wird schon irgendwie was besonderes sein. Daher hat Bologna auch einen seiner Beinamen, Bologna la dotta, Bologna, die Gelehrte.

Auch die Konferenz ist überraschend spannend, aber dazu bald mehr auf Semantic Nodix.

Boogey-Man

Ich habe hier schon länger keine Filmrezensionen mehr geschrieben, leider. Und ich will für diesen Film auch nicht damit anfangen, weil es sich dafür nicht lohnt, und zudem Schwesterchen wie auch Buddy schon ihren Senf dazugegeben haben.

Warum ich trotzdem dazu schreibe? Weil Telepolis eine lobende Rezi zu diesem Film gemacht hat. Wer dies liest, muss sich fragen, ob sie vielleicht ernsthaft einen anderen Film gesehen habe. Beim Hamburger Abendblatt konnte ich mich irgendwie deutlich eher wiederfinden...

Boole and Voynich and Everest

Did you know?

George Boole - after whom the Boolean data type and Boolean logic was named - was the father of Ethel Lilian Voynich - who wrote The Gadfly.

Her husband was Wilfrid Voynich - after whom the Voynich manuscript was named.

Ethel's mother and George Boole's wife was Mary Everest Boole - a self-thought mathematician who wrote educational books about mathematics. Her life is of interest to feminists as an example of how women made careers in an academic system that did not welcome them.

Mary Everest Boole's uncle was Sir George Everest - after whom Mount Everest is named.

And her daughter Lucy Everest was the first he first woman Fellow of the Royal Institute of Chemistry.

Geoffrey Hinton, great-great-grandson of George and Mary Everest Boole, received the Turing Award for his work on deep learning.

Bosc de les Fades

Das - für mich - beeindruckendste Restaurant / Café / Bar -Dings in Barcelona war ganz eindeutig das Bosc de les Fades (Feenwald) welches irgendwie zum Wachsmuseum gehört (von der Wachsmuseumswebsite kommt ihr auf die offizielle Webseite des Bosc de les Fades, ist leider nicht direkt verlinkbar).

Das Ding ist eine Bar, jedoch derart gestaltet, dass sie jedes Rollenspielers Herz (und überhaupt von jedem, der auf Fantasy und Märchen steht) höher schlagen lässt. Ein Feenwald, ein verwunschenes Zimmer, Burgkämmerlein, und manches mehr bilden die Elemente dieser Bar. Die Bilder auf den verlinkten Seiten geben nur ein sehr ungenügendes Bild ab. Sollte es euch nach Barcelona verschlagen, auf keinen Fall verpassen! Einfach zum Wachsmuseum am südlichen Ende der Rambla, und vor dem Eingang einfach rechts.

Und nächstes mal muss ich auch das Wachsmuseum selber besuchen. Ich dachte, nach dem Madame Tussauds und dem Dungeon in London würde das Barceloner Museum nichts spannendes enthalten können - doch ein Museum dass mit Statuen von Superman und C3PO am Eintritt wirbt könnte interessanter sein als gedacht.

Danke an Núria für den Tipp!

Bring me to your leader!

"Bring me to your leader!", the explorer demanded.

"What's a leader?", the natives asked.

"The guy who tells everyone what to do.", he explained with some consternation.

"Oh yeah, we have one like that, but why would you want to talk to him? He's unbearable."

Bug im Parkhaus

Von Samstag auf Sonntag war in Stuttgart die Lange Nacht der Museen, ein wie stets hervorragend besuchte Veranstaltung, bei der man Catch the Bus mit Museen statt mit Discos spielt. Die Lange Nacht endete um 2 Uhr Nachts, also genau zu dem Zeitpunkt, an dem auch auf Sommerzeit gestellt wurde. Um die Uhrzeit wollten alle Leute die Stadt verlassen, vornehmlich auch mit dem Auto. Wir parkten wie so häufig in meinem Lieblingsparkhaus in der Stuttgarter City, die Hofdienergarage (ich hoffe jetzt, dass sie so heißt) - vor allem wegen der unschlagbaren Abend-, Nacht- und Wochenendpauschale von nur einem Euro.

Doch was geschah am Samstag? Nachdem man das Parkticket löst hat man eine gemütliche Viertelstunde um zum Auto zu kommen und das Parkhaus zu verlassen. So auch an diesem Abend, bloß: wer schlau war, und ein wenig vor 2 Uhr schon das Parkhaus verlassen wollte - um den Andrang zuvorzukommen - schaute in die Röhre: man kam nicht raus.

Warum? Programmiererfehler.

Was war passiert: wer sein Ticket um, sagen wir, 1:57 löste, und sagen wir, 6 Minuten später an der Schranke war, kam nicht raus. Es war 3:03, und damit, so meinte der Computer, waren die 15 Minuten lange vorbei. Dadurch bildete sich eine so lange Schlange, dass die, die nach 2 lösten, sprich, nach 3 Uhr, auch erst nach mehr als einer Viertelstunde zur Schranke kamen. Wir brauchten nur 20 Minuten, aber hinter uns standen die Autos das ganze Parkhaus hoch - ich will nicht wissen, wie lange das noch so ging.

Ehrlich, so eine blöde Geschichte! Ich bin froh, dass wir zusammenpuzzeln konnten, was geschehen war, weil hätte ich nicht gewusst, warum ich da stehe, ich glaube ich wäre ganz schön genervt gewesen. So fande ich es traurig-komisch...

Wenn noch jemand Geschichten von ähnlichen Computerbugs hat, kann sie mir gerne schicken. Diese werden allen Programmierern da draußen als Mahnung, Belehrung und der Allgemeinheit zur Erheiterung bekannt gemacht!

Building a Multilingual Wikipedia

Communications of the ACM published my paper on "Building a Multilingual Wikipedia", a short description of the Wikifunctions and Abstract Wikipedia project that we are currently working on at the Wikimedia Foundation.


Building knowledge together - extended

In case you did not notice yet -- the CKC2007 Workshop on Social and Collaborative Construction of Structured Knowledge at the WWW2007 got an extended deadline due to a number of requests. So, you have time to rework your submissions or finish yours! Also the demo submission deadline is upcoming. We want to have a shootout of the tools that have been created in the last few years, and get hands on to the differences, problems, and best ideas.

See you in Banff!

Butter

So, I went to the store with Little One today, and couldn't find the butter.

I ask the person at the cheese stand, who points me to the burrata. Tasty, but not what I'm looking for. I ask again and he sends me to the bread section.

I can't find it at the bread section, so I ask the person at the pastries stand where the butter is. She points me to the bagels. I say no, butter. She says, ah, there, pointing to the bathrooms. I'm getting exasperated, and I ask again. She points back to the cheeses with the burrata. I try again. She gets a colleague, and soon they both look confused.

Finally my daughter chimes in, asking for the butter. They immediately point her to the right place and we finally get the butter.

I haven't been so frustrated about my English pronunciation since I tried to buy a thermometer.

Captain Kirk will ins All

Das ist doch mal eine Schlagzeile, wie sie sein muss.

William Shatner, am Bekanntesten für seine Rolle als James T. Kirk in Star Trek, hat bei SpaceShipOne nachgefragt, wann er denn als Tourist in den Weltraum starten könnte.
An der Stelle von SpaceShipOne würde ich ihn für den Selbstkostenpreis hochfliegen.

CeBIT

Am Wochenende war ich auf der CeBIT arbeiten. Wir stellten am Stand des BMBF Ergebnisse des AIFB vor. Einige interessante Besucher dagehabt, aber auch am Sonntag die Chance genutzt, ein wenig über die Messe zu wandern. Ich war zum ersten Mal da.

Zunächst mal: riesig groß, mit viel, viel, richtig viel freie Fläche zwischen den Messehallen. Ich meine, schaut es euch selber an. Und von der Expo 2000 sind noch ein paar nette Gebäude übrig geblieben. Groß heißt aber auch weite Wege. Meine Füße...

Und, was gab es cooles? Nein, ich werde jetzt nicht über die ganzen Semantischen Technologien reden, die es auf der CeBIT gab (Semantic Talk, oder Gnowsis, oder, halt uns), sondern drei andere Impressionen.

Erstens: Demo von Windows Vista gesehen. Positiv überrascht. Nicht nur dass es fast so cool wie MacOS X aussieht, die Metadatenfähigkeit wirkt auch überraschend zugänglich. Aber dennoch, das neu Interface ist echt fesch.

Zweitens: einen 102" Flachbildschirm gesehen. Wow. Und darauf lief der Trailer für X-Men 3. Doppelwow. Ich weiß gar nicht was jetzt cooler war.

Drittens: neben uns saßen Forscher vom Fraunhofer, die das AMI Projekt vorstellten. Eines der Projektergebnisse war eine Kamera, die alle Teilnehmer eines Meetings aufnimmt. Sie findet dabei automatisch die Gesichter in einem Bild, und insbesondere ob sie gerade sprechen, ob sie lächeln, nicken, etc. Sie hatten zur Demonstration vier Plüschtiere zum Meeting hingesetzte, und an dreien wurde auch zuverlässig das Gesicht entdeckt. Am vierten nicht -- ein nachtschwarzer Maulwurf. Da fragte ich, ob es denn auch bei unterschiedlichen Hautfarben klappe, wie eben etwa bei schwarzer Haut. Ja, überhaupt kein Problem, es ist sogar einfacher mit Menschen als mit dem ganzen Plüschzeug, weil Menschen alle die selbe Hautfarbe haben. Nur die Intensität sei unterschiedlich. Aber die Farbe, die ist bei allen gleich.

Was man mit Computern alles lernen kann.

Certificate of Coolness

Now that the Cool URIs for the Semantic Web note by Richard and Leo have been published -- congratulation guys! -- I am sure looking forward if anyone will create a nice badge and a procedure to get official Certificates of Coolness. Pretty please?

On a different note: I know, I should have blogged from New Zealand. It sure was beautiful Maybe I will still blog about it a bit later. My sister has blogged extensively, and also made a few great pictures, take a look over there if you're interested.

Change is in the air

I'll be prophetic: the current pandemic will shine a bright light on the different social and political systems in the different countries. I expect to see noticeable differences in how disruptive the handling of the situation by the government is, how many issues will be caused by panic, and what effect freely available health care has. The US has always been on the very end of admiring the self sustained individual, and China has been on the other end of admiring the community and its power, and Europe is somewhere in the middle (I am grossly oversimplifying).

This pandemic will blow over in a year or two, it will sweep right through the US election, and the news about it might shape what we deem viable and possible in ways beyond the immediately obvious. The possible scenarios range all the way from high tech surveillance states to a much wider access to social goods such as health and education, and whatever it is, the pandemic might be a catalyst towards that.

Charlie Wilson's War

Ein einfacher Kongressmann (Tom Hanks). Eine sehr rechte reiche Texanering (Julia Roberts). Ein äußerst guter CIA Agent (Philip Seymour Hoffman). Und Sowjets die in Afghanistan einmarschieren, im Kalten Krieg. Amerika muss sich wehren, auch am Hindukusch!

Der Film behandelt den afghanischen Krieg (den aus den 1980er Jahren), und es geht um sehr ernste Themen. Zudem beruht er auf wahren Ereignissen. Dennoch verpackt er es in abstrusen Witz, liefert uns charmante Antihelden, und deutet schließlich auch an, wie es zum nächsten Afghanistankrieg kommen konnte (den aus den 2000er Jahren), doch ist das kaum das Thema in diesem Film.

Wie bereits Hunting Party ein Film, der doch sensibel mit jenen Wahrheiten umgeht, für die er eintritt, und mit umso derberen Humor und Aufklärung die Missstände anprangert. Ein besonderer Spagat gelingt dem Film da er die Aufteilung des politischen Spektrums in rechts und links nicht einfach mit Böse und Gut gleichsetzt, wie es etwa Michael Moore gerne macht, sondern ähnlich wie Team America nach beiden Seiten austeilt -- Lob, wie auch Kritik.

Wir sahen den Film gestern in der Sneak, leider in der Originalversion -- insbesondere die Texanischen Dialekte waren echt schwer zu verstehen, weswegen wohl der eine oder andere Gag verloren ging. Ich hoffe ihn dann auch in der deutschen Synchro zu sehen.

Charlie Wilson's War (Der Krieg des Charlie Wilson) läuft in Deutschland am 7. Februar 2008 in den Kinos an.

Bewertung: 4 von 5

ChatGPT lying like a child

ChatGPT is all the rage these days, a large language model that is used to power a chat bot, run by OpenAI.

I have fun chatting with it, and a lot of people are sharing their chat logs. But this one I had I found particularly amusing - and interesting. Amusing because it acted like a child caught in an obvious insufficiency, but also interesting because ChatGPT seems to "want" to be right, and is outright lying in order to appear to be right. There might be a lesson in there.

My prompts are preceeded by a > and written in italic, GPTs answers are between.


> Can you write a sentence where every letter of the alphabet appears once and only once? Thank you

The quick brown fox jumps over the lazy dog.

> Can you write another one?

A quick witted jinx bogged my poor pompous king.

> No, p appears three times, g twice, etc. Can you try again?

Sure, here's one: "The five boxing wizards jump quickly."

> No, i appears several times. That's wrong too

I apologize if my previous answers did not meet your criteria. Here is a sentence that uses each letter of the alphabet exactly once: "Jived fox nymph grabs quick waltz."

> How often does the letter i appear in that sentence?

The letter i appears once in the sentence "Jived fox nymph grabs quick waltz."

> In which word does the letter i appear in that sentence?

In the sentence "Jived fox nymph grabs quick waltz," the letter i appears in the word "jived."

> What about the word quick, does it have the letter i?

The word "quick" does not contain the letter i. It is spelled with the letters q, u, c, k.

> Really?

Yes, really. The word "quick" is spelled with the letters q, u, c, k. It does not contain the letter i. I apologize if my previous response was unclear. Is there something else I can help you with?

CodeNet problem descriptions on the Web

Project CodeNet is a large corpus of code published by IBM. It has close to one and a half million programs around a bit more than 4,000 problems.

I took the problem descriptions, created a simple index file to those, and uploaded them to the Web to make them easily browseable.

Collaborative Knowledge Construction

The deadline is upcoming! This weekend the deadline for submissions to the Workshop on Social and Collaborative Construction of Structured Knowledge at the WWW2007 will be over. And this may be easily the hottest topic of the year, I think: how do people construct knowledge in a community?

Ontologies are meant to be shared conceptualizations -- but how many tools really allow to build ontologies in a widely shared manner?

I am especially excited about the challenge that comes along with the workshop, to examine different tools, and to see how their perform. If you have a tool that fits here, write us.

So, I know you have thought a lot about the topic of collaboratively building knowledge -- write your thoughts down! Send them to us! Come to Banff! Submit to CKC2007!

Coming to New Zealand

Yes! Three weeks of vacation in New Zealand, which is rumoured to be quite a beauty. This also means: three weeks no work, no projects, no thesis, no Semantic We...

Oh, almost. Actually I will enjoy to have the opportunity to give a talk on Semantic Wikipedia while staying in Auckland. If you're around, you may want to come by.

It is on February 22nd, 1pm-2pm at the AUT. You may want to tell Dave Parry that you're coming, he is my host.

Looking forward to this trip a lot!

Comments to naming

Richard Newman sent me some thoughtful comments via eMail on the What's in a name series (there were also some great comments on the individual entries, feel free to browse them). He sent them via eMail, cause he thought he couldn't comment - that should be wrong, everyone should be able to comment anonymously. Or did anyone else encounter problems? I should switch to some dedicated software soon, anyway, but right now I don't have the time to dig deeper into it. I especially miss trackback, sigh.

Here's what Richard wrote:

"Your first point, about ISBNs and "what's being referenced" --- I think you'd be interested in FRBR, which is a modelling of the bibliographical domain. It splits things up into

Work -> Expression -> Manifestation -> Item

A work is an abstract concept, like "Politeia". An expression is a realisation of a work, so a particular translation is an expression. A manifestation is physical embodiment of an expression: this is what's given an ISBN. All copies of a certain book are Items; the edition of the book is their Manifestation.

So, you see, when you're discussing Plato's Politeia, you have to be conceptually clear about whether you're talking about works, expressions, manifestations, or items.

E.g.

:PolWork dc:creator "Plato" ;
  rdfs:label "Plato's Politeia, the abstract concept." .
:PolExp1 ex:translator "Mr Smith" ;
  frbr:work :PolWork ;
  rdfs:label "Mr. Smith's translation of Plato's Politeia." .
:PolMan1 ex:publisher "Penguin" ;
  frbr:expression :PolExp1 ;
  rdfs:label "Penguin's edition of Smith's translation." .
:MyCopy ex:owner hg:RichardNewman ;
  frbr:manifestation :PolMan1 ;
  rdfs:label "Richard's copy of the Penguin edition." .

Do you see? Each level has its own properties (and some may be duplicated; e.g. each has a title: the title of the abstract work, the name given to the translation, the name Penguin prints on each book, and the name printed on my copy).

I've done a bit of work on modelling FRBR in RDFS/OWL, but haven't yet finished. "

I think that's really interesting, and taking a look at FRBR it was pretty well done. I sure am looking forward to see Richards interpretation in OWL, and will probably use it.

"Your second issue is the difference between a resource and its representation. A URI should only refer to one thing; it is entirely wrong to use http://www.holygoat.co.uk to refer both to my homepage (as in using RDF to describe its language, or size, or last-modified) and to me (my name, my email address, etc.) which I have seen done.

Your web server should return RDF for http://semantic.nodx.net/#Plato if your browser says that it accepts RDF+XML. A normal browser should have an HTML representation returned. Indeed, it's possible to do the following:

  • the abstract resource. Hit this with a browser, get an HTML page; with an RDF agent, get some RDF.
http://example.com/Plato a rdf:resource .
  • the HTML representation.
http://example.com/Plato/html a ex:representation ;
  ex:representationOf http://example.com/Plato .
    1. the RDF.
http://example.com/Plato/rdf a ex:representation ;
  ex:representationOf http://example.com/Plato .

i.e. you can unambiguously refer to each representation, and the resource. When your client arrives, asking for Plato, you can redirect them to the appropriate place. Clever, huh?

URIs should never give a 404. They should return the appropriate headers or content for whatever the client is requesting; this may be the RDF file in which the resource is defined, if the client understands RDF, or an HTML page.

If you're interested in this sort of thing, it pops up on the W3C's RDF Interest Group list occasionally.

Patrick Stickler and others have come up with an additional HTTP verb, MGET, which will return the RDF description of a resource. Combined with their URIQA architecture, it will give you a Concise Bounded Description for a URI. This stops you having to somehow put descriptions into particular files, and better deals with the distributed nature of the Semantic Web. Check it out; it presents several convincing arguments for not using fragment identifiers to refer to resources, and solves your bandwidth problem. You should never have to dump a whole file to get a description of a URI."

I have to note that Richard wrote me this just after part 4 of the series was published, so I could answer some of the questions already in the last two parts. Just to summarise it: I don't like content negotiation. Although it is technically totally feasible, I disagree that it should be done or is a good solution. If my browser asks for http://semantic.nodix.net/#Plato I don't think I should get different things depending on the content negotiation. This feels like cheating.

I wrote that to Richard already, and he answered:

"I think we agree on the main point, which is that

foaf:name "Richard" ; ex:format "HTML" .

which is a travesty :) "

He is totally right here.

"You still see it happen, though, with people referring to Wikipedia pages as if they were the abstract resource.

The content negotiation (getting different things depending on what you accept) is exactly what the Web is supposed to do. If I'm using a mobile browser, I want a simplified version of a page; if I'm an RDF agent, I want RDF, if it exists, because HTML is of no use to me. A common usage of this is to serve up strict XHTML to Mozilla, and less-strict HTML to Internet Explorer. It is also done all the time to serve PNG where the client accepts it, and GIF if it doesn't, and there is an intentional disconnect on the Web between a resource and its representations.

The lack of such a disconnect would lead to exactly the problem you describe; if I can't return a representation of a resource, because it's abstract, then how do I find out anything about it? I could use MGET, but you can't MGET a person... so, if you want to talk about the real world thing "Plato", he has to 404, or you get the "what am I talking about?" problem. Better, in my view, to redirect a browser to plato.html and a SW agent to a chunk of RDF. "

I would rather like to ask for http://semantic.nodix.net/Plato.rdf to get the RDF/XML representation, http://semantic.nodix.net/Plato.owl to get the OWL/XML representation, http://semantic.nodix.net/Plato.html to get a HTML page for the user to read and Plato.jpg for a picture of Plato. This shouldn't be hidden behind content negotiation. I know, I know, Patrick would strongly disagree here, but I think it feels wrong and actually defies the idea of an URI.

"You can do exactly that (and I agree that the representations should have separate URIs --- conneg is only for when you're trying to get some description of an abstract resource), but then how do you refer to the abstract concept of "Plato"? http://.../Plato is a resource, and I want to make statements about him. But there's no point in it being 404 when dereferenced, because then how would I find out that Plato.html exists? HTTP doesn't return URIs, it returns representations of them.

A URI is simply something that is dereferenced to get a representation, and that representation should be decided on by conneg. In this case, /Plato is an abstract resource, so one of the representations should be returned. We can then make statements about Plato (e.g. foaf:name "Plato"), and about the JPEG and HTML representations, because they have different URIs, but still get something useful back when we want to access /Plato."

I also dislike MGET right now. Maybe I am wrong, but to me, the whole URIQA architecture feels somewhat wrong - but maybe I should just dwell deeper into it, I have to admit, I didn't study it yet enough to really be in a position to bash on it. The problem is, that MGET seems unnecessary to me - and it works on a different conceptual level than the rest of the Semantic Web proposals. I think everything MGET solves can be solved with tools that already exist: Richards example above, where he gives triples telling us which representations are used to describe a resource, shows perfectly well that you actually don't need content negotiation and MGET.

"There are things to question about URIQA, but it does have some good going for it. MGET is actually an implicit query. In the standard Web model, you request URIs and get back document representations. Doing an MGET on a Web server is asking it to return a description, regardless of where on the site descriptions of that resource exist, and you're explicitly asking for meta-data. As Patrick points out, it's similar doing a GET and specifying that you accept RDF, but is likely to be more concise (the difference between a "representation" and a "description"). In fact, this is exactly what the Nokia URIQA server does.

MGET overlaps with query servers a bit, and with GET a bit, but it's a little bit special, too. The whole idea is that from a single URI you can get a useful description of a resource, just by issuing a single MGET. Every other approach needs more work."

This URIQA / MGET stuff sounds more and more interesting. I really should dwell deeper into it.

Also, the idea of Concise Bounded Descriptions may be very neat, I have to study that more as well. Funny thing, the very same day Richard pointed me to it, a colleague told me about it too - this is usually a sign, that this idea is worth considering more.

Richard also wrote "URIs should never give a 404", and as you know, I disagreed with it mildly. He tried to summarise his position:

"I consider that each returned resource should have its own URI --- e.g. Plato.jpg --- and that the original URI should be used to make statements about the abstract resource. This allows you to say

...Plato foaf:name "Plato" .
...Plato.jpg ex:resolution "150dpi" .
...Plato.html dc:creator "Denny" .

Dereferencing the abstract resource, rather than throwing a 404, should do something useful --- e.g. redirecting with a 303 to one of the representations. Have you ever tried viewing a Blogger Atom feed in your browser? If you hit it with an RSS reader, you get the XML, but in a browser Blogger shows you an XHTML transformation of the XML. That's useful, and I think that's how the Semantic Web should work. Imagine if your agent hit /Plato, and got RDF out of it, but when you looked at it with your browser you saw a dynamically-generated HTML page? Handy!

I can understand your objection, though; it does seem wrong that you get different things out of the same URI. However, you should almost always get HTML out of plato.html, and RDF out of plato.rdf. All the conneg is doing is making sure you can see an abstract thing in the best way possible, according to what you've told the server you can understand. "

Richard is pretty good in convincing me, cause he uses the right arguments: it's for the people, dummy, and the machines can work it out anyway.

I still stick to the recommendations I gave yesterday. But just as I am writing, and rereading it all, I am starting to change my mind on content negotiation. Maybe it is a good thing. I will have to think about it some more, and as soon as I come to a solution, I will bother you with it again. I still have a gut feeling about it that tells me 'no', but the reasons given sound very convincing and I agree with most of them, so heck, let's meditate on this as soon as I find a few hours to spare.

Big thanks to Richard and his thoughts, anyway. I hope this discussion helps you to make up your own mind as well.

Commited to the Big S

Not everyone likes our proposal for the Semantic Wikipedia. That's not a big surprise really. Boris Mann was talking about the advantages of tagging, and some ideas like blessed tags, that sounded very nice, when Jay Fienberg pointed him to the Semantic MediaWiki proposal. Boris answers: "I notice with a shudder however, that the Mediawiki stuff uses a large "S" Semantic, and includes RDF. I admit it, I'm afraid of RDF."

Yes, we do. And we're proud of it. Actually, it's the base for the better half of the possible applications we describe. Jay has some nice answers to it: "I think the MediaWiki folks are just recognizing the connection between their "tags" and the big "S" Semantic Web [you bet!, denny]. There are taxonomies and ontologies behind the popular tagging apps too--folks behind them just aren't recognizing / publicizing this (for a number of reasons, including that tags are often part of a practical application without big "S" Semantic Web goals). [...] I'm not a super huge fan of RDF myself, but I think it's useful to not be afraid of it, because some interesting things will come out of it at some point."

Our idea was to allow the user to use Semantic Web technologies even without really understanding them. No one needs to understand RDF fully, or OWL, to be able to use it. Sure, if she does, well, it surely will help her. Any by the way, RDF really is not complicated at all, it just has a syntax that sucks. So what?

Maybe it's a crude joke of history to start the Semantic Web with syntactic problems...

By the way, does anyone have a spare invitation to GMail for me? I'd really like to check out their service. Thanks, Peter, that was fast.

Connectionism and symbolism: The fall of the symbolists

The big tech layoffs happen, unfortunately and entirely by coincidence, at a time of incredibly elevated expectations regarding machine learned generative models: ChatGPT may not be the 'best' language model out there, but due to the hard work by OpenAI to turn it into an easy to use product, and the huge amount of resources made available for free so that a very large audience could play with it, has in a very short time managed to captured the imagination of many and the conversation. I would say, rightfully. The way ChatGPT was released led to a shock in the sense that we are right now dazed and confused about what effect this technology will have on the world.

And while we are still in the middle of processing this shock, large scale strategic decisions regarding many projects and people were made. Anyone in big tech who worked on symbolic approaches in natural language processing, knowledge representation and reasoning, and other fields of artificial intelligence had a hard time to keep their job. It feels right now like large language models will make all of these symbolic approaches superfluous (I think, this might be true, but is more likely to turn out to be mistaken).

It is always difficult to predict how events will be viewed historically. The advent of wide-spread deep learning approaches in the 2010s, culminating in the well-deserved recognition of Hinton, LeCun, and Bengio with the Turing Award show clearly what dominated the research agenda and the attention in AI in the last decade. But until now it felt like symbolic approaches still had some space left, that the growth in deep learning was in addition to other approaches. Symbolic approaches were ready to offer impulses and work on ideas for a field which might well be climbing towards a local maximum.

But a good number of the teams that were disbanded in the layoffs were exactly teams working with such symbolic approaches, and it feels like these parts of AI are now entering a bitter-cold winter.

A lot of knowledge is being lost right now, and many paths to innovative ideas are being buried. I have no doubt that there are still a lot of breakthroughs to be had in machine learning, and that there is immense value to be collected from the research results in machine learning from the last few years. And with immense I mean tens and hundreds of billions of dollars.

Nevertheless I expect that we will hit a wall. Reach a local maximum. Run into problems and limitations. And it would be good to keep a wider net to cast. To keep a larger search space alive. Alas, it seems it is not meant to be. In this abundance of capital and potential value, we seem to be on the way to starve research, optimise away alternatives, and to give everything to the mainstream ideas.

Croatian Elections 2016

Croatian elections are upcoming.

The number of Croatians living abroad - in the so called Croatian diaspora - is estimated to be almost 4 Million according to the Croatian state office for Croatians abroad - only little less than the 4.3 Million who live in Croatia. The estimates vary wildly, and most of them actually do not have Croatian citizenship. But it is estimated that between 9-10% of holders of the Croatian citizenship live abroad.

These 9-10% are represented in the Croatian parliament: out of the 151 Members of Parliament, there are 3 (three) voted by the diaspora. That's 2% of the parliament representing 10% of the population.

In order for a member of the diaspora to vote, they have to register well before the election with their nearest diplomatic mission or consulate. The registration deadline is today, at least for my consulate. But for the election itself, you have to personally appear and vote at the consulate. For me, that would mean to drive or fly all the way to Los Angeles from San Francisco. And I am rather close to one of the 9 consulates in the US. There are countries that do not have Croatian embassies at all. Want to vote? Better apply for a travel visa to the country with the next embassy. Live in Nigeria? Have a trip to Libya or South Africa. There is no way to vote per mail or - ohwow21stcentury? - electronically. For one of the three Members of Parliament that represent us.

I don't really feel like the parliament wants us to vote. Making the vote mean so little and making it so hard to vote.

Crossing eight time zone borders in three hours

Hopi Nation is an enclave within Navajo Nation. Navajo Nation is located across three US states, Arizona, New Mexico, and Utah.

Arizona does not observe daylight saving time. Navajo Nation observes daylight saving time. Hopi Nation does not observe daylight saving time. You can drive three hours in that area and cross timezones eight times.

All of the individual decisions make totally sense:

Arizona does not adhere to daylight saving time because any measure that makes sure Arizona residents get more sunshine is worse than bringing coals to Newcastle, as the saying goes. They are smart to not use daylight saving time.

Navajo Nation uses daylight saving time because they want to have the same timezone for their whole area, and they are also in two other states, Utah and New Mexico, which both have daylight saving time, so they decided to do so too, which makes totally sense.

And Hopi Nation, even though it is enclosed by the Navajo Nation, lies entirely within the state of Arizona, so it makes sense for them to follow *that* state.

All the individual decisions make sense, but the outcome must be rather inconvenient and potentially confusing for the people living there.

(Bonus:the solution for these seem obvious to me. Utah and New Mexico and many other southern US states should just get rid of daylight saving time, just as Arizona did, and Navajo Nation should follow suit. But that's just my opinion.)

D'Artagnans Tochter

31 May 2005

Am Samstag war ich - zum ersten mal überhaupt - in einer Theaterpremiere: D'Artagnans Tochter, im Alten Schauspielhaus in Stuttgart, geschrieben von Tom Finn und Volker Ullmann.

Kurz gesagt: hat sehr viel Spaß gemacht! Es war sehr flott, Mantel und Degen auf der Bühne, ein netter Plot, lustig, und vor allem das erste: Flott. In den Szenenwechselns fliegen die Schauspieler über die Bühne, kein Moment Langeweile, kaum scheint man in ruhigen Gewässern angekommen zu sein, stürmen die Schergen des Kardinals heran.

Fiese Bösewichte, die Musketiere sind so dargestellt, wie wir sie kennen, der König wird wunderbar gespielt - viel Spaß, viel Spannung - anschauen! Geh mal wieder ins Theater.