Semantic search

Jump to navigation Jump to search

Kebab Connection

aus der Reihe Filme in 50 Worten

Montag, Sneak im Metropol. Eine der Regeln der Sneak: ein Film, der eine Preview bekommt, kommt nicht in der Sneak. Wurde Montags gebrochen.

Zum Glück. Weil den Film hätte ich sonst nicht gesehen. Dem Titel nach erwartete ich eine platte Komödie über Türken der zweiten Generation, die voll auf cooler Lan, blöde Sprüche, und zwischen den Knöcheln hängende Hosen stehen. Stattdessen: ein witziger Film, mit einer glaubhaften Geschichte, der Klischees nicht nur bedient, sondern sie an den richtigen Stellen auch ernst nimmt und konsequent weitertreibt. Wenn der Vater den Sohn als Sohn eines Esels beschimpft, weil er weiß, dass er im Unrecht ist, oder er verzweifelt versucht, seine Fehler wegzuerklären, weil er zu stolz ist, sie als solche zuzugeben, dann sehen wir überzeugend dargestellte Szenen. Kurz: ein wirklich guter Film, der leider wegen des Marketings und des Titels den größten Teil der potenziellen Zuschauer verfehlen könnte.

Keine Spielmesse

Dieses Jahr komme ich doch nicht auf die Essener Spielemesse. Geld, Wetter, Reisemöglichkeit, Zeit, usf., mögen mir keine rechte Gelegenheit geben. Schade, wollte ich doch einige Leute sprechen...

Nun ja, was soll's, nächstes Jahr hoffentlich wieder. Und jetzt noch die Treffen absagen...

Keine Updates

Weiterhin keine großen Updates, ich habe für die Uni noch einiges aufzuholen. Aber wie auch schon letzte Woche kommt pünktlich ein neuer nutkidz-Comic!

Keynote at SMWCon Fall 2020


I have the honor of being the invited keynote for the SMWCon Fall 2020. I am going to talk "From Semantic MediaWiki to Abstract Wikipedia", discussing fifteen years of Semantic MediaWiki, how it all started, where we are now - crossing Freebase, DBpedia, Wikidata - and now leading to Wikifunctions and Abstract Wikipedia. But, more importantly, how Semantic MediaWiki, over all these years, still holds up and what its unique value is.

Page about the talk on the official conference site: https://www.semantic-mediawiki.org/wiki/SMWCon_Fall_2020/Keynote:_From_Semantic_Wikipedia_to_Abstract_Wikipedia

Keynote at Web Conference 2021

Today, I have the honor to give a keynote at the WWW Confe... sorry, the Web Conference 2021 in Ljubljana (and in the whole world). It's the 30th Web Conference!

Join Jure Leskovec, Evelyne Viegas, Marko Grobelnik, Stan Matwin and myself!

I am going to talk about how Abstract Wikipedia and Wikifunctions aims to contribute to Knowledge Equity. Register here for free:

Update: the talk can now be watched on VideoLectures:

Kill Bill Vol. 2

Huch. Gestern wollte ich eigentlich in Kill Bill Vol. 1 - stattdessen rutschte ich in Kill Bill Vol. 2. Macht nichts, dacht ich mir, habe ich hier halt im Rahmen der Filme in 50 Worten, voller stolz...

Ein Film, wo ich von der Story noch weniger verraten darf als sonst, sonst werde ich womöglich geköpft. Und das ist bei den potenziellen Zuschauern dieses Filmes nicht aus der Luft gegriffen! Wer Teil 1 geliebt hat, der wird auch Teil 2 mögen! Megacoole Actionszenen. Heiße Musik. Wunderschöne Aufnahmen. Geradlinger (für einen Tarantino, meine ich) Handlungsbogen. Schnelle Duelle. Was den Inhalt angeht: nun ja, der Titel verrät eigentlich schon ziemlich alles...

Kurz: wer Teil 1 gesehen hat, weiß eh, ob er hier reingeht oder nicht. Wozu also noch groß rezensieren?
Das einzig überraschende mag sein, dass der Film - ein zweiter Teil, wohlgemerkt - ab 16 Jahren freigegeben ist, während der erste ab 18 war.

Kindheitsträume wahr werden lassen

Randy Pausch ist Professor für User Interfaces and der CMU, einer der bekanntesten Universitäten der USA. Im September 2006 wurde bei ihm Bauchspeicheldrüsenkrebs diagnostiziert. Seitdem kämpft er um jeden Tag.

In der Vortragsreihe Journeys (Reisen) der CMU, welche Randy mit seinem Vortrag eröffnete, sollen die Vortragenden sich überlegen, was sie den Zuhörern sagen würden, wenn dies ihre letzte Gelegenheit für einen Vortrag wäre. Ihr Erbe, sozusagen.

Der Vortrag -- auch wenn er knappe anderthalb Stunden dauert -- stellt flott und unterhaltend Randys Kindheitsträume vor, und wie sie wahr geworden sind, oder nicht. Er erzählt viele Anekdoten, und fasst wichtige Weisheiten zusammen.

Das Video des Vortrags, mit Untertiteln in Deutsch oder Englisch, ist bei Google Video erhältlich. Sehenswert.

Kleeblatt Versand

Heute erhielt Schwesterchen einen Brief mit einer "Letzten Anweisung für Ihren Gewinn-Abruf". Ihre Gewinnnummer hatte nämlich Glück und brachte ihre einen "Anteils-Gewinn aus der großen 1.618,00 Euro Super-Jackpot-Vergabe"! Toll, oder? 1618 Euro! Da freut man sich. Besonders, wenn man nicht mitgespielt hat.
Wie stets ist der Teufel im Detail: schauen wir mal genauer nach, was hier der Kleeblatt Versand aus Graz durch die Bundesrepublik schickt.
Zunächst mal ist das ganze nicht durch einen Notar, sondern durch einen offiziellen Rechtsberater bestätigt. Nein, nicht, dass ich glaube, der Kleeblatt Verlag würde hier lügen und betrügen, und deswegen nicht einmal einen richtigen Notar hinzuziehen - beileibe nicht! Eher, dass ein Notar wohl zu teuer gewesen wäre, und die ganze Aktion ja - wie es in den Regeln ausdrücklich steht (die in unleserlichen Majuskeln in Hellgrau auf der Rückseite des zweiten Blattes stehen) - "zum Zweck der Gewinnung von neuen Kunden und Interessierten durchgeführt", und die Aktion natürlich am Besten so billig wie möglich sein soll.

"Wie aber?", fragt man sich. "Ich habe doch gewonnen! Ich brauche nur diese 0190er Nummer anrufen, und ich kriege meinen Gewinn!" - ja, schon. Dieser Gewinn aber ist ein Anteil der 1618 Euro. Und der Anruf geht an eine 0190er Nummer, die 1,86 Euro die Minute kostet. Lassen wir den Anruf, sagen wir mal, sechs Minuten dauern (ist nicht lang: Buchstabieren des Namens, der Adresse, es wird nach ein paar Daten gefragt, die im Brief verteilt sind, vielleicht am Anfang noch ein wenig - ebenso zahlungspflichtige, musikuntermalte "Bitte Warten"-Schleifen - und prompt sind 10 Euro unterwegs.
"10 Euro? Das ist doch OK, wenn man 1618 Euro bekommt. Ich meine, die habe ich doch sicher!" Falsch! Man hat einen Anteils-Gewinn an den 1618 Euro erhalten. Das heißt, wenn nur 1000 Leute aus ganz Deutschland anrufen - eine lächerlich kleine Zahl bei einer so überzeugend wirkenden Gewinnmitteilung - bekommt jeder 1,61 Euro. Das heißt, jeder - bis auf den Kleeblatt-Versand. Der kassierte durch die Anrufe über 10.000 Euro.

"Aber wenn das jetzt bekannt ist, dann rufen doch weniger an, und mein Anteil wächst" - oder alternativ "Der macht das doch nur, um seinen eigenen Anteil zu erhöhen, und will, dass wir alle nicht anrufen!" Hier kämen wir in ein klassisches Problem der Spieltheorie: machen wenige mit, ist der Gewinn des Einzelnen größer, aber wenn viele mitmachen etc. Dazu gibt es ausreichend theoretische Texte, ich will hier nicht weiter darauf eingehen.
Zumal das hier nicht zutrifft: ich kann mit Nodix gar nicht die Massen erreichen, welche diesen Gewinn-Abruf erhalten, dazu habe ich schlicht nicht die Reichweite. Ein paar hundert Leser am Tag, das ist nicht das Ding.
Zweitens: ich werde nicht teilnehmen (weil ich ja gar keine Einladung erhalten habe) und ich werde auch Schwesterchen davon abraten. Ich schreibe das also nicht aus persönlichem Interesse, zumal, wie eben gesagt, dass auch nicht wirklich helfen würde.

Alles, was ich mit diesem Beitrag wollte, ist auf die schiere Frechheit zu verweisen, mit der hier Gutgläubigkeit ausgeschlachtet wird. Der Kleeblatt Versand missbraucht hier, um an bestätigte Adressen zu gelangen - nichts Anderes ist ihr Ziel - die Naivität der Leute. Dies führt zu mehr Misstrauen in der Welt. Nein, es ist kein Betrug, glaube ich - ich bin kein Rechtsanwalt - weil alle Informationen ja korrekt da stehen. Sie sind aber irreführend, und ich bin mir sicher, dass jeder Teilnehmer mit einem wesentlich größeren Gewinnanteil rechnet, als den, den er erhalten wird.
Natürlich, wie stets gilt: "Der Rechtsweg ist ausgeschlossen. Teilnehmer oder Dritte können nicht auf die Zuteilung eines bestimmten Gewinnes klagen. Jeder Teilnehmer bestätigt mit seiner Teilnahme, dass er die Teilnahmebedingungen gelesen und verstanden hat, anerkennt und akzeptiert."
Wozu also noch beschweren?

Ich würde mich freuen, wenn ihr diesen Beitrag verlinkt, wenn ihr die Möglichkeit habt. Auch dürft ihr ihn kopieren und sinnerhaltend kürzen und widergeben, solange mein Name oder ein Link hierher angegeben ist. Auf so einen Schmarrn - wie man in Graz sagen würde - sollte man deutlich hinweisen!
Danke.


Ursprünglich auf Nodix von Denny veröffentlicht.

Vorhergehender Beitrag:
Nachfolgender Beitrag:


Kleinigkeiten

Und immer noch am Kleingikeiten basteln. Der Counter, der fleißig seit knapp zwei Jahren die Besucher zählt, hat jetzt auch einen netten Verlauf erhalten, und die Titelseite wurde stark verkleinert, indem die Texte ins Archiv geschoben wurden. Dadurch sollte sich die Ladezeit für die Titelseite stark verkürzen. Zudem ist das Baumgarfbanner nach einem Tag Dienst wieder gewechselt worden - von Grün zu Blau. Stets eine Kleinigkeit, und alles wird besser mit der Zeit...

Klickfrei

Sehr coole Designidee: eine Webseite, die man vollständig navigieren kann, ohne zu klicken, dontclick.it. Sehr schnell, sehr flüssig und sehr hübsch. Ich stelle mir jetzt noch vor, dass wir keine Maus haben, sondern versuchen, mit unseren Augen den Cursor zu steuern - und schon haben wir ein extrem futuristisches User Interface...

Hilft auch bei RSI.

Knowledge Graph Conference 2019, Day 1

On Tuesday, May 7, began the first Knowledge Graph Conference. Organized by François Scharffe and his colleagues at Columbia University, it was located in New York City. The conference goes for two days, and aims at a much more industry-oriented crowd than conferences such as ISWC. And it reflected very prominently in the speaker line-up: especially finance was very well represented (no surprise, with Wall Street being just downtown).

Speakers and participants from Goldman Sachs, Capital One, Wells Fargo, Mastercard, Bank of America, and others were in the room, but also from companies in other industries, such as Astra Zeneca, Amazon, Uber, or AirBnB. The speakers and participants were rather open about their work, often listing numbers of triples and entities (which really is a weird metric to cite, but since it is readily available it is often expected to be stated), and these were usually in the billions. More interesting than the sheer size of their respective KGs were their use cases, and particularly in finance it was often ensuring compliance to insider trading rules and similar regulations.

I presented Wikidata and the idea of an Abstract Wikipedia as going beyond what a Knowledge Graph can easily express. I had the feeling the presentation was well received - it was obvious that many people in the audience were already fully aware of Wikidata and are actively using it or planning to use it. For others, particularly the SPARQL endpoint with its powerful visualization capabilities and the federated queries, and the external identifiers in Wikidata, and the approach to references for the claims in Wikidata were perceived as highlights. The proposal of an Abstract Wikipedia was very warmly received, and it was the first time no one called it out as a crazy idea. I guess the audience was very friendly, despite New York's reputation.

A second set of speakers were offering technologies and services - and I guess I belong to this second set by speaking about Wikidata - and among them were people like Juan Sequeda of Capsenta, who gave an extremely engaging and well-substantiated talk on how to bridge the chasm towards more KG adoption; Pierre Haren of Causality Link, who offered an interesting personal history through KR land from LISP to Causal Graphs; Dieter Fensel of OnLim, who had a a number of really good points on the relation between intelligent assistants and their dialogue systems and KGs; Neo4J, Eccenca, Diffbot.

A highlight for me was the astute and frequent observation by a number of the speakers from the first set that the most challenging problems with Knowledge Graphs were rarely technical. I guess graph serving systems and cloud infrastructure have improved so much that we don't have to worry about these parts anymore unless you are doing crazy big graphs. The most frequently mentioned problems were social and organizational. Since Knowledge Graphs often pulled data sources from many different parts of an organization together, with a common semantics, they trigger feelings of territoriality. Who gets to define the common ontology? What if the data a team provides has problems or is used carelessly, who's at fault? What if others benefit from our data more than we did even though we put all the effort in to clean it up? How do we get recognized for our work? Organizational questions were often about a lack of understanding, especially among engineers, for fundamental Knowledge Graph principles, and a lack of enthusiasm in the management chain - especially when the costs are being estimated and the social problems mentioned before become apparent. One particularly visible moment was when Bethany Sehon from Capital One was asked about the major challenges to standardizing vocabularies - and her first answer was basically "egos".

All speakers talked about the huge benefits they reaped from using Knowledge Graphs (such as detecting likely cliques of potential insider trading that later indeed got convicted) - but then again, this is to be expected since conference participation is self-selecting, and we wouldn't hear of failures in such a setting.

I had a great day at the inaugural Knowledge Graph Conference, and am sad that I have to miss the second day. Thanks to François Scharffe for organizing the conference, and thanks to the sponsors, OntoText, Collibra, and TigerGraph.

For more, see:

Knowledge Graph Technology and Applications 2019

23 May 2019

Last week, on May 13, the Knowledge Graph Technology and Applications workshop happened, co-located with the Web Conference 2019 (formerly known as WWW), in San Francisco. I was invited to give the opening talk, and talked about the limits of Knowledge Graph technologies when trying to express knowledge. The talk resonated well.

Just like in last week's KGC, the breadth of KG users is impressive: NASA uses KGs to support air traffic management, Uber talks about the potential for their massive virtual KG over 200,000 schemas, LinkedIn, Alibaba, IBM, Genentech, etc. I found particularly interesting that Microsoft has not one, but at least four large Knowledge Graphs: the generic Knowledge Graph Satori; an Academic Graph for science, papers, citations; the Enterprise Graph (mostly LinkedIn), with companies, positions, schools, employees and executives; and the Work graph about documents, conference rooms, meetings, etc. All in all, they boasted more than a trillion triples (why is it not a single graph? No idea).

Unlike last week, the focus was less on sharing experiences when working with Knowledge Graphs, but more on academic work, such as query answering, mixing embeddings with KGs, scaling, mapping ontologies, etc. Given that it is co-located with the Web Conference, this seems unsurprising.

One interesting point that was raised was the question of common sense: can we, and how can we use a knowledge graph to represent common sense? How can we say that a box of chocolate may fit in the trunk of a car, but a piano would not? Are KGs the right representation for that? The question remained unanswered, but lingered through the panel and some QnA sessions.

The workshop was very well visited - it got the second largest room of the day, and the room didn’t feel empty, but I have a hard time estimating how many people where there (about 100-150?). The audience was engaged.

The connection with the Web was often rather tenuous, unless one thinks of KGs as inherently associated with the Web (maybe because they often could use Semantic Web standards? But also often they don’t). On the other side it is a good outlet within the Web Conference for the Semantic Web crowd and to make them mingle more with the KG crowd, I did see a few people brought together into a room that often have been separated, and I was able to point a few academic researchers to enterprise employees that would benefit from each other.

Thanks to Ying Ding from the Indiana University and the other organizers for organizing the workshop, and for all the discussion and insights it generated!

Update: corrected that Uber talked about the potential of their knowledge graph, not about their realized knowledge graph. Thanks to Joshua Shivanier for the correction! Also added a paragraph on common sense.

Komplette nutkidz

Yeah! Die nutkidz sind wieder vollständig online. Alle bisherigen 38 Folgen, in deutsch und in englisch.

Und das beste: Gerüchten zufolge soll bald sogar eine neue Folge kommen... ;)

Kroatiens erste drei WM Spiele 2006

Gestern wurde ich durch die Nachricht, dass die WM Gruppen ausgelost werden, eher überrascht (Dank an Rudi für den Hinweis), aber jetzt bin ich über die Ergebnisse erfreut - das werden sehr schöne Spiele!

Berlin, Dienstag, 13. Juni, 20 Uhr: Brasilien gegen Kroatien

Yeah! Das Megaspiel für Kroatien. Der amtierende Weltmeister. Der Favorit. Die Nummer 1 der Weltrangliste. Das erste Spiel auf der WM für beide Länder. Gab es schon mal ein Spiel zwischen den beiden? Nicht in einem offiziellen Turnier. Aber es gab ein Freundschaftsspiel letztes Jahr. Ergebnis? 1:1. Na, nichts ist unmöglich!

Nürnberg, Sonntag, 18. Juni, 14 Uhr: Japan gegen Kroatien

Die Japaner haben wir schon mal besiegt - nur ist das schon ein paar Jahre her, und es war knapp. Beim ersten Auftritt der Kroaten und der Japaner bei einer WM. Doch diesmal sind die Vorzeichen umgedreht. Japan ist Nummer 15 auf der Weltrangliste, Kroatien die 20. Es wird ein enges Spiel. Und - auch Japan konnte dieses Jahr beim Confederations Cup gegen Brasilien ein 2:2 rausholen, und hätte gar fast gewonnen...

Stuttgart, Donnerstag, 22. Juni, 20 Uhr: Kroatien gegen Australien

Ein Heimspiel für die Kroaten. Und in der kroatischen Mannschaft steckt nicht nur ein Australier kroatischer Herkunft. Die Australien waren ganz schön angekäst, als Australier wieder nach Kroatien zurückwanderten, weil sie dort in der Nationalmannschaft vorankommen konnten. Jetzt wird sich Australien rächen wollen. Aber in Stuttgart hat Kroatien eine große kroatische Gemeinde in der Hinterhand. Nur - wird schwerlich dieses Spiel entscheidend werden.

Eine starke Gruppe - aber es gibt ja auch keine leichten Gruppen mehr. Ein klarer Favorit. Aber es kommt auch der Zweite weiter. Noch sechs Monate, dann rollt der Ball!

Und ich interessiere mich gar nicht für Fußball.

Kroatiens nächsten drei WM Spiele 2006

Nachdem gestern die ziemlich sicheren Spiele aufgeschrieben wurde, hier der weitere Verlauf für Kroatien. Gewisse Diskrepanzen zur Realität können sich durch Tatsachen einstellen.

Kaiserslautern, Montag, 26. Juni, 16 Uhr, Zweite Runde: Italien gegen Kroatien

Haushoher Favorit des Spiels ist klar der mehrfache Weltmeister. Die Italien sind jedoch etwas zu leichtherzig, und Kroatien schafft es den alten Nachbar gegenüber der Adria zu besiegen. Das Spiel wird als SmartWeb Demonstrationsobjekt benutzt (erstes K.O.-Spiel in Kaiserslautern!), doch das geht unter weil es danach zu Schlägereien und Randalen kommt in verschiedenen deutschen Städten. Sehr traurig so was.

Hamburg, Freitag, 30. Juni, 20 Uhr, Viertelfinale: Kroatien gegen Frankreich

Mal wieder ein Weltmeister. Diesmal will Frankreich die Schlappe in 2002 wettmachen, doch Kroatien ist in Hochform nach den bisherigen Spielen. Doch es ist eine Wiederholung der WM 1998. Damals besiegte Kroatien im Viertelfinale den Favoriten Deutschland, und verlor dann im Halbfinale gegen den späteren Weltmeister Frankreich. So auch hier. Im Viertelfinale besiegen wir den Favoriten!

München, Mittwoch, 5. Juli, 20 Uhr, Halbfinale: Kroatien gegen Brasilien

Das wir die Brasilianer auch dummerweise jetzt schon wiedertreffen müssen! Im Finale wäre es doch viel spannender. Beide Mannschaften haben eine regelrechte Odyssee durch Deutschland hinter sich gebracht, um sich nach dem Eröffnungsspiel in Berlin hier in München wieder zu begegnen. Wer darf wieder nach Berlin? - nur, diesmal zum Finale. Am Tag zuvor konnte sich Deutschland als einer der beiden Finalteilnehmer qualifizieren - und wer wird nun den Gastgeber im Finale fordern? Alle tippen auf den Weltmeister.

Letztes Spiel wird dann entweder in Stuttgart gegen Holland um Platz Drei, oder in Berlin gegen Deutschland um den Titel. Egal wie es ausgeht: das Spiel wird am nächsten Tag Schlagzeilen machen!

La Grande seduction

aus der Reihe Filme in 50 Worten

Ein kleines Dorf weit, weit ab vom Schuss, mit etwas mehr als 100 Einwohner (bei Bedarf auch doppelt so viele), stirbt langsam vor sich hin. Als es darum geht, eine Fabrik hier anzusiedeln, fehlt vor allem eines - ein ansässiger Arzt. Durch einen dummen Zufall kommt ein schickimicki Schönheitschirurg in das Dorf, und die Dorfbewohner versuchen alles, davon zu überzeugen, dass dies der beste Ort auf Erden ist...

Sympathisch, lustig, unterhaltsam. Man hätte die Figuren vielleicht noch ein wenig überspitzter erwartet, die ganze Geschichte noch absurder gestaltet, den Humor etwas schwärzer - aber stattdessen blieb der Film stets in einem realistischen, wohligen Rahmen. Sehenswert.

Ab dem 2. Dezember im Kino.

Ladenschlussträume

Ich moechte ein Land, wo ich um 21:15 in eine Buchhandlung laufen kann, um mich umzuschauen. Ich moechte ein Land, in dem ich abends nicht in die Stadt hetzen muss, weil die Laeden zu sind.
Ach, halt. In so einem Land bin ich ja!
Also, umformulieren: ich moechte, dass auch endlich in Deutschland das Ladenschlussgesetz gekippt wird. Mehr Freiheit fuer alle!

Und ehrlich: ich glaube nicht, dass es der Untergang des Abendlandes waere, wenn neben den Taxifahrern, Hoteliers, Krankenschwestern, Kellnern, Reportern, Journalisten, Aerzten, Schaffnern, Busfahrern, Feuerwehrmaennern, Polizisten, Bauern, Schichtarbeitern, Webmastern, Freischaffenden, Schluesseldiensten, Telefonsexanbietern, Selbststaendigen, Pfarrern und vielen anderen auch die Einzelhandelsfachverkaeufer Sonntags und abends arbeiten wuerden.

Lange Nacht der Museen

Ist es eigentlich Etikettenschwindel bei der langen Nacht der Museen von einer lange Nacht zu sprechen? Die hört ja schon um 2 auf!

Gestern war in Stuttgart wieder die Lange Nacht der Museen. Diesmal leider ohne mich, da ich in Karlsruhe noch auf der DenkWerkzeug 2005 war (die wiederum einige Aha-Erlebnisse und interessante Einsichten erbrachte), und ich erst nach Mitternacht in Stuttgart aufschlug (weil ich nicht bedachte, dass Samstags die Züge anders fahren).

Hätte sie wirklich lange gedauert, wäre ich noch hingegangen. Für anderthalb Stunden aber 12 Euro auszugeben, nun ja, ich weiß nicht. Ironisch: die Rückfahrt dauerte dann fast so lange, wie die Museumsnacht noch ging, weil am Schlossplatz eine Bahn entgleist war.

Zur langen Nacht der Museen muss immer etwas passieren, wie etwa vor zwei Jahren, als das Parkhaus uns nicht rausließ.

Languages with the best lexicographic data coverage in Wikidata 2023

Languages with the best coverage as of the end of 2023

  1. English 92.9%
  2. Spanish 91.3%
  3. Bokmal 89.1%
  4. Swedish 88.9%
  5. French 86.9%
  6. Danish 86.9%
  7. Latin 85.8%
  8. Italian 82.9%
  9. Estonian 81.2%
  10. Nynorsk 80.2%
  11. German 79.5%
  12. Basque 75.9%
  13. Portuguese 74.8%
  14. Malay 73.1%
  15. Panjabi 71.0%
  16. Slovak 67.8%
  17. Breton 67.3%

What does the coverage mean? Given a text (usually Wikipedia in that language, but in some cases a corpus from the Leipzig Corpora Collection), how many of the occurrences in that text are already represented as forms in Wikidata's lexicographic data.

The list contains all languages where the data covers more than two thirds of the selected corpus.

Last Unicorn dreamcast

One thing my sister and I were doing from time to time was to think, if the Last Unicorn was remade as a live action movie, who would we cast in the different roles? It is sad to see how many of our dreamcast have since died: our favorite Prince Lir was Heath Ledger, and King Haggard, unsurprisingly, Christopher Lee.

Since I was reading the book with Little One, and now watched the movie again (for the 120th time or so), I was again going through my current dreamcast. Here we go.

  • Lady Amalthea - Anna Taylor-Joy
  • Schmendrick - Zach Braff, Donald Glover
  • Molly Grue - Mia Farrow
  • Prince Lir - Owen Wilson, no, getting too old; Liam Hemsworth? Chloe Moretz would be an interesting choice
  • King Haggard - Anthony Hopkins, Jack Nicholson

Since it is en vogue, I also asked Bard and ChatGPT. Here's Bard:

  • Jeff Bridges as Schmendrick the Magician
  • Mia Farrow as Molly Grue
  • Angela Lansbury as the Unicorn
  • Daryl Hannah as Filidor
  • Jeff Goldblum as Schmendrick's sidekick, Bungle
  • Peter Dinklage as the Red Bull
  • Uma Thurman as Mommy Fortuna
  • Alan Rickman as King Haggard

OK, Alan Rickman is a great choice, but unfortunately dead. Uma Thurman as Mommy Fortuna is weird. Peter Dinklage as the Red Bull... why does the Red Bull need to be cast at all? Who are Bungle and Filidor? Angela Lansbury as the Unicorn / Lady Amalthea is... not the right choice. Also dead. Mia Farrow and Jeff Bridges are too obvious choices given their roles in the cast of the animation movie, also Angela Lansbury is from the original cast. I would give Bard a D for that answer.

ChatGPT says:

  • Unicorn - Saoirse Ronan or Emma Watson
  • Schmendrick - Timothee Chalamet or Eddie Redmayne
  • Molly Grue - Meryl Streep or Helen Mirren
  • King Haggard - Ian McKellen or Christopher Lee (if he were still alive)
  • Prince Lir - Tom Holland or Ansel Elgort
  • Mommy Fortuna - Tilda Swinton or Cate Blanchett

Not even close to my choice, but heck, those are good choices. Molly Grue and Mommy Fortuna seem both a bit over-cast. Prince Lir and Schmendrick are pretty brilliant choices. I am not particularly impressed by Emma Watson for Lady Amalthea, I could see Saoirse Ronan work.

I'd give a B+ to ChatGPT.

I feel like ChatGPT seems to go for actors and actresses that are popular with the crowd who likes The Last Unicorn? Not the worst choice.

I followed up with Bard to see who Bungle and Filidor are, because they don't appear neither in the book nor in the movie, if I remember correctly. So, "Bungle is a red unicorn who is Schmendrick's sidekick in the novel The Last Unicorn. He is a clumsy and incompetent unicorn, but he is also a loyal and brave friend. Bungle is played by Jeff Goldblum in the 1982 animated film adaptation of the novel." And "Filidor is a bard in the novel The Last Unicorn. He is a wandering minstrel who travels the land singing songs and telling stories. Filidor is a wise and kind-hearted man, and he is always willing to help those in need. He is played by Daryl Hannah in the 1982 animated film adaptation of the novel." That's entirely a fabrication.

Lautlos

aus der Reihe Filme in 50 Worten

Ein Serienkiller. Ein absoluter Profi, der seit seinem 10. Lebensjahr mordet. Der keine Spuren hinterlässt. Der sich dummerweise in eine im Schlaf summende Frau verliebt, und ihr dann nicht nur nicht das Leben nimmt, sondern auch noch das ihre rettet, damit sie ihm das seine retten kann. Doch die Polizei ist hinter ihnen her, darunter auch ein ausgebuffter, mit geradezu übersinnlich erscheinenden Fähigkeiten ausgestatteter Kommisar, der immer die richtige Theorie tippt. Wird er ein neues Leben beginnen können, oder wird ihn seine Vergangenheit einholen?

Joachim Krol spielt den emotionslosen Killer perfekt. Selbst wenn er sich verliebt, ist er vollkommen überzeugend emotionslos. Die Vorschau auf diesen Film hat so gewirkt, als ob nach Lola rennt, Goodbye Lenin oder Liegen Lernen mal wieder ein überraschend guter deutscher Film ins Kino rollt, der Germanikus ungeschehen macht. Nö. Ich meine, er ist besser als Germanikus, ja, aber das sagt mehr über Germanikus als über Lautlos. Die Liebesgeschichte scheint vollkommen unmotiviert, und außer ein halbes Dutzend guter Dialogzeilen wird in dem Film gar nichts geboten. Lautlos ist Aktionslos, Spannungslos, Herzschmerzlos und Humorlos. Das witzigste an dem Film ist noch das nach Specht klingende Instrument des Soundtracks. Also, nicht dass er grottig schlecht ist. Aber ich freue mich doch sehr, dass es eine kostenlose Preview des Filmes war, und nicht etwa eine Samstagabendfastzehneuroteurevorstellung.
Nee, Liebesgeschichte und Polizeiarbeit vermengt zur Zeit das schon laufende Taking Lives wesentlich besser als Lautlos.


Ursprünglich auf Nodix von Denny veröffentlicht.

Vorhergehender Beitrag:
Nachfolgender Beitrag:


Lebenssituation

Nur zu euer aller Update: ich habe inzwischen mein Studium der Philosophie und Informatik abgeschlossen und habe jetzt eine Stelle an der Fakultät für Wirtschaftswissenschaften, an der ich - so alles gut geht - den Doktor in Politk machen werde (eine Stelle, über die ich übrigens wirklich irre glücklich bin).

Im Ernst.

Übrigens, ich werde am Wochenende auf dem RatCon sein, wer mich dort treffen will, schreibe mir eine kurze eMail.

Legolas ist gar nicht so toll

Wer erlegt in dem Film "Der Herr der Ringe Teil 3: Die Rückkehr des Königs" eigenhändig einen Olifanten?

Genau, Éowyn - sie braucht dafür etwa 10 Sekunden, und Éomer, der in etwa derselben Zeit sogar zwei Stück auf einmal erledigt.
Ach ja, da wäre noch Legolas, der ungefähr zwei Minuten lang auf einem Olifanten rumhüpft, während dieser weiter durch die eigenen Kampfesgefährten rast, bis er ihn endlich zu Fall bringt.

Was lernen wir daraus? Es kommt weniger darauf an, was man erreicht hat, als darauf, wie man es verkauft.

Lexical masks in JSON

We have released lexical masks as ShEx files before, schemata for lexicographic forms that can be used to validate whether the data is complete.

We saw that it was quite challenging to turn these ShEx files into forms for entering the data, such as Lucas Werkmeister’s Lexeme Forms. So we adapted our approach slightly to publish JSON files that keep the structures in an easier to parse and understand format, and to also provide a script that translates these JSON files into ShEx Entity Schemas.

Furthermore, we published more masks for more languages and parts of speech than before.

Full documentation can be found on wiki: https://www.wikidata.org/wiki/Wikidata:Lexical_Masks#Paper

Background can be found in the paper: https://www.aclweb.org/anthology/2020.lrec-1.372/

Thanks Bruno, Saran, and Daniel for your great work!

Libertarian cities

I usually try to contain my "Schadenfreude", but reading this article made it really difficult to do so. It starts with the story of Rio Verde Foothills and its lack of water supply after it was intentionally built to circumvent zoning regulations regarding water supply, and lists a few other examples, such as

"Grafton, New Hampshire. It’s a tiny town that was taken over by libertarians who moved there en masse to create their vision of heaven on earth. They voted themselves into power, slashed taxes and cut the town’s already minuscule budget to the bone. Journalist Matthew Hongoltz-Hetling recounts what happened next:
'Grafton was a poor town to begin with, but with tax revenue dropping even as its population expanded, things got steadily worse. Potholes multiplied, domestic disputes proliferated, violent crime spiked, and town workers started going without heat. ...'
Then the town was taken over by bears."

The article is worth reading:

The Wikipedia article is even more damning:

"Grafton is an active hub for Libertarians as part of the Free Town Project, an offshoot of the Free State Project. Grafton's appeal as a favorable destination was due to its absence of zoning laws and a very low property tax rate. Grafton was the focus of a movement begun by members of the Free State Project that sought to encourage libertarians to move to the town. After a rash of lawsuits from Free Towners, an influx of sex offenders, an increase of crime, problems with bold local bears, and the first murders in the town's history, the Libertarian project ended in 2016."

Lion King 2019

Wow. The new version of the Lion King is technically brilliant, and story-wise mostly unnecessary (but see below for an exception). It is a mostly beat-for-beat retelling of the 1994 animated version. The graphics are breathtaking, and they show how far computer-generated imagery has come. For a measly million dollar per minute of film you can get a photorealistic animal movies. Because of the photorealism, it also loses some of the charm and the emotions that the animated version carried - in the original the animals were much more anthropomorphic, and the dancing was much more exaggerated, which the new version gave up. This is most noticeable in the song scene for "I can't wait to be king", which used to be a psychedelic, color shifted sequence with elephants and tapirs and giraffes stacked upon each other, replaced by a much more realistic sequence full of animals and fast cuts that simply looks amazing (I never was a big fan of the psychedelic music scenes that were so frequent in many animated movies, so I consider this a clear win).

I want to focus on the main change, and it is about Scar. I know the 1994 movie by heart, and Scar is its iconic villain, one of the villains that formed my understanding of a great villain. So why would the largest change be about Scar, changing him profoundly for this movie? How risky a choice in a movie that partly recreates whole sequences shot by shot?

There was one major criticism about Scar, and that is that he played with stereotypical tropes of gay grumpy men, frustrated, denied, uninterested in what the world is offering him, unable to take what he wants, effeminate, full of cliches.

That Scar is gone, replaced by a much more physically threatening scar, one that whose philosophy in life is that the strongest should take what they want. Chiwetel Ejiofor's voice for Scar is scary, threatening, strong, dominant, menacing. I am sure that some people won't like him, as the original Scar was also a brilliant villain, but this leads immediately to my big criticism of the original movie: if Scar was only half as effing intelligent as shown, why did he do such a miserable job in leading the Pride Lands? If he was so much smarter than Mufasa, why did the thriving Pride Lands turn into a wasteland, threatening the subsistence of Scar and his allies?

The answer in the original movie is clear: it's the absolutist identification of country and ruler. Mufasa was good, therefore the Pride Lands were doing well. When Scar takes over, they become a wasteland. When Simba takes over, in the next few shots, they start blooming again. Good people, good intentions, good outcomes. As simple as that.

The new movie changes that profoundly - and in a very smart way. The storytellers at Disney really know what they're doing! Instead of following the simple equation given above, they make it an explicit philosophical choice in leadership. This time around, the whole Circle of Life thing, is not just an Act One lesson, but is the major difference between Mufasa and Scar. Mufasa describes a great king as searching for what they can give. Scar is about might is right, and about the strongest taking whatever they want. This is why he overhunts and allows overhunting. This is why the Pride Lands become a wasteland. Now the decline of the Pride Lands make sense, and also why the return of Simba and his different style as a king would make a difference. The Circle of Life now became important for the whole movie, at the same time tying with the reinterpretation of Scar, and also explaining the difference in outcome.

You can probably tell, but I am quite amazed at this feat in storytelling. They took a beloved story and managed to improve it.

Unfortunately, the new Scar also means that the song Be Prepared doesn't really work as it used to, and thus the song also got shortened and very much changed in a movie that became much longer otherwise. I am not surprised, they even wanted to remove it, and now I understand why (even though back then I grumbled about it). They also removed the Leni Riefenstahl imaginary from the new version which was there in the original one, which I find regrettable, but obviously necessary given the rest of the movie.

A few minor notes.

The voice acting was a mixed bag. Beyonce was surprisingly bland (speaking, her singing was beautiful), and so was John Oliver (singing, his speaking was perfect). I just listened again to I can't wait to be king, and John Oliver just sounds so much less emotional than Rowan Atkinson. Pity.

Another beautiful scene was the scene were Rafiki receives the massage that Simba is still alive. In the original, this was a short transition of Simba ruffling up some flowers, and the wind takes them to Rafiki, he smells them, and realizes it is Simba. Now the scene is much more elaborate, funnier, and is reminiscent of Walt Disney's animal movies, which is a beautiful nod to the company founder. Simba's hair travels with the wind, birds, a Giraffe, an ant, and more, until it finally reaches the Shaman's home.

One of my best laughs was also due to another smart change: in Hakuna Matata, when they retell Pumbaa's story (with an incredibly cute little baby Pumbaa), Pumbaa laments that all his friends leaving him got him "unhearted, every time that he farted", and immediately complaining to Timon as to why he didn't stop him singing it - a play on the original's joke, where Timon interjects Pumbaa before he finishes the line with "Pumbaa! Not in front of the kids.", looking right at the camera and breaking the fourth wall.

Another great change was to give the Hyenas a bit more character - the interactions between the Hyena who wasn't much into personal space and the other who rather was, were really amusing. Unlike with the original version the differences in the looks of the Hyenas are harder to make out, and so giving them more personality is a great choice.

All in all, I really loved this version. Seeing it on the big screen pays off for the amazing imagery that really shines on a large canvas. I also love the original, and the original will always have a special place in my heart, but this is a wonderful tribute to a brilliant movie with an exceptional story.

Little One's first GIF

Little One made her first GIF!

cat.gif

Little Richard and James Brown

When Little Richard started becoming more famous, he already had signed up for a number of gigs but was then getting much better opportunities coming in. He was worried about his reputation, so he did not want to cancel the previous agreed gigs, but also did not want to miss the new opportunities. Instead he sent a different singer who was introduced as Little Richard, because most concert goers back then did not know how Little Richard exactly looked like.

The stand-in was James Brown, who at this point was unknown, and who later had a huge career, becoming an inaugural inductee to the Rock and Roll Hall of Fame - two years before Little Richard.

(I am learning a lot from and am enjoying Andrew Hickey's brilliant podcast "A History of Rock and Roll in 500 Songs")

Live from ICAIL

"Your work remindes me a lot of abduction, but I can't find you mention it in the paper..."

"Well, it's actually in the title."

Long John and Average Joe

You may know about Long John Silver. But who's the longest John? Here's the answer according to Wikidata: https://w.wiki/4dFL

What about your Average Joe? Here's the answer about the most average Joe, based on all the Joes in Wikidata: https://w.wiki/4dFR

Note, the average height of a Joe in Wikidata is 1,86cm or 6'1", which is quite a bit higher than the average height in the population. A data collection and coverage issue: it is much more likely to have the height for a basketball player than for an author in Wikidata.

Just two silly queries for Wikidata, which are nice ways to show off the data set and what one can do with the SPARQL query endpoint. Especially the latter one shows off a rather interesting and complex SPARQL query.

Love is...

"Love is what's in the room with you at Christmas if you stop opening presents and listen."

Angeblich aus einer Studie, in der 4- bis 8-jährige Kinder gefragt wurden, was Liebe ist. Herzallerliebst.

Leider konnte ich die Originalstudie nicht finden - vielleicht schafft es jemand anderes ja - aber der Text wird ständig im Netz zitiert: hier, hier hier, hier oder hier, aber auch hier. Google findet über 60.000 Treffer... wahrscheinlich, dass der Text erfunden ist.

Trotzdem schön, ihn zu lesen.

Lucky Luke gegen die Daltons

Wie meistens montags, auch gestern in der Sneak gewesen. In letzter Zeit gab es - wie man im Notausgang-Blog oder auf nakit-arts mitbekommen konnte - einige echt geniale Filme: 11:14, Mr and Mrs Smith, L.A. Crash, The Fantastic Four, Nicotina, Antikörper, Madagascar, Hitchhikers Guide through the Galaxy oder Garden State. Gestern war der Film nicht ganz so gut.

Genau genommen war er grottig. Ich schreibe ja schon länger keine Filmrezis mehr, weil die Filmrezis auf Baumgarf deutlich besser sind. Ja, klar, ich stimme ihm nicht immer zu, aber meistens. So auch bei den Daltons. Einen so schlechten Film habe ich sehr selten - vielleicht noch nie - gesehen. Auf imdb gibt es eine Rezi mit dem Titel "Not ENTIRELY bad", wobei ich ein Wort aus der Überschrift streichen würde (und es ist nicht das großgeschriebene). Ansonsten sind die Meinungen auf imdb über den Film sehr deutlich: 40% haben dem Film die schlechtesmögliche Note gegeben. Reicht nicht, um den Film in Top 100 der schlechtesten Filme zu katapultieren, überraschenderweise. Ich kenne davon - soweit ich mich erinnere - aber nur einen Film, Alone in the Dark (ich weiß nicht mehr, welche Police Academy-Teile ich gesehen habe). Ob der wirklich schlechter ist? Müsste ich nochmals sehen, um das zu beurteilen. Sprich, ich werde es nie, nie, nie erfahren...

Warum sind die Daltons so grottig schlecht? Erstens, wie bei Clever & Smart schon, hat irgendjemand den Darstellern gesagt: hey, das ist eine Comicverfilmung. Also müsst ihr alle wie doof rumhüpfen und euch seltsam bewegen. Zweitens, wozu Gags? Die Vorlage hat doch schon genug davon. Drittens, die beiden Szenen, die ausnahmsweise gute sind, also die, wo Lucky Luke Joe Dalton das Serum verabreicht und wo Joe Dalton die Gulch Bank für den finalen Überfall betritt, zeigen, dass die Leute es offenbar besser draufhaben. Warum also machen sie es nicht?

Das, was ich wirklich schade finde, sind, dass 27 Millionen Dollar reingeflossen sind und hunderte von Menschen mitgewirkt haben. Muss dann das Ergebnis nicht wie Verrat vorkommen? Oder glauben diese Leute wirklich, dass sie einen guten Film gemacht haben? Darf oder muss man mit ihnen Mitleid haben? Die glauben doch an ihre Arbeit. Wie also kann so ein Murks überhaupt entstehen?

Dafür immerhin einen Narnia-Trailer (hier ist die deutsche Version verlinkt) gesehen. Auf französisch. Sah sehr vielversprechend aus. Endlich darf auch Disney ein Fantasy-Meisterwerk verfilmen, nachdem Tolkien das für den Herrn der Ringe ja testamentarisch ausgeschlossen hatte.

Machine Learning and Metrology

There are many, many papers in machine learning these days. And this paper, taking a step back, and thinking about how researchers measure their results and how good a specific type of benchmarks even can be - crowdsourced golden sets. It brings a convincing example based on word similarity, using terminology and concepts from metrology, to show how many results that have been reported are actually not supported by the golden set, because the resolution of the golden set is actually insufficient. So there might be no improvement at all, and that new architecture might just be noise.

I think this paper is really worth the time of people in the research field. Written by Chris Welty, Lora Aroyo, and Praveen Paritosh.

Madrid Stadt

Mein letzter Blogeintrag aus Madrid war ja eher ein Schnellschuss aus dem Flughafen, diesmal habe ich ein wenig mehr Zeit. Das Hotel in dem ich abgestiegen bin, ansonsten brauchbar, wenn auch nichts besonderes - ich wuerde es nicht weiterempfehlen - hat laut Website Internetanschluss in allen Zimmern und WLAN. Was sie nicht haben, ist beides zusammen, WLAN auf dem Zimmern also, sondern man muss mit seinem Modemkabel in die Wand stoepseln. Und was sie auch auf der Website verschweigen ist der eher unhoefliche Preis von 9 Euro die Stunde...

Aber zurueck zu Madrid. Die Stadt selbst hat ein paar Autos zu viel, dafuer aber sprechen viel zu wenig Menschen Englisch. Na, was gehe ich auch ohne spanisch zu koennen nach Spanien koennte man einwerfen. Aber das Museum de Prada ist wirklich sehenswert: Velazquez Familia sieht so beeindrucken aus, wie ich sie mir vorgestellt habe, die Werke von Goya sind auf zwei Stockwerken ausgestellt: die lustigen, bunten ganz oben, die duesteren, wie der weit bekannte Saturn, darunter, in duesteren Raeumen. Sehr beeindruckend. Und die gewaltige Sammlung von Rubensbildern, allein die Menge an mythischen Figuren - wow. Da moechte man am liebsten nochmal ein Mythologielexikon rausgraben und sich darin eingraben.

Auch der Retito, der grosse Park in Madrid: sehr schoen, beeindruckend, gross. Nicht so gross wie der Stuttgarter Stadtpark, aber welche Stadt hat schon einen solch grossen Park? Die moderne Kathedrale der Stadt ist ebenfalls sehr auffaellig, einfach weil sie ganz anders ist als andere Kathedralen. Blau aufgemalte Himmelsflaechen? Sehr cool. Aber auch nur wegen der Einzigartigkeit, zugegeben.

Wenn man mich fragt, was ich mit Madrid verbinde, habe ich auch eine ganz deutliche Antwort.

Durst.

Mail problems

The last two days my mail account had trouble. If you could not send something to me, sorry! Now it should work again.

Since it is hard to guess who tried to eMail me in the last two days (I guess three persons right), I hope to reach some this way.

Major bill for US National Parks passed

Good news: the US Senate has passed a bipartisan large Public Lands Bill, which will provide billions right now and continued sustained funding for National Parks.

There a number of interesting and good parts about this, besides the obvious that National Parks are being funded better and predictably:

  1. the main reason why this passed and was made was that the Evangelical movement in the US is increasingly reckoning that Pro-Life also means Pro-Environment, and this really helped with making this bill a reality. This is major as it could set the US on a path to become a more sane nation regarding environmental policies. If this could also extend to global warming, that would be wonderful, but let's for now be thankful for any momentum in this direction.
  2. the sustained funding comes from oil and gas operations, which has a certain satisfying irony to it. I expect this part to backfire a bit somehow, but I don't know how yet.
  3. Even though this is a political move by Republicans in order to safe two of their Senators this fall, many Democrats supported it because the substance of the bill is good. Let's build on this momentum of bipartisanship.
  4. This has nothing to do with the pandemic, for once, but was in work for a long time. So all of the reasons above are true even without the pandemic.

Map of current Wikidata edits

It starts entirely black and then listens to Wikidata edits. Every time an item with a coordinate is edited, a blue dot in the corresponding place is made. So slowly, over time, you get a more and more complete map of Wikidata items.

If you open the developer console, you can get links and names of the items being displayed.

The whole page is less than a hundred lines of JavaScript and HTML, and it runs entirely in the browser. It uses the Wikimedia Stream API and the Wikidata API, and has no code dependencies. Might be fun to take a look if you're so inclined.

https://github.com/vrandezo/wikidata-edit-map/blob/main/index.html

Marketing

Das nenn ich mal Cross-Marketing par excellence: passend zum aktuellen Film von Mel Gibson gibt es jetzt sogar das dazugehörige Getränk, Fanta Citrell Passion Fruit.
Und wenn wir schon bei dem Film sind: bei so einem Erfolg muss es doch auch eine Fortsetzung geben. Wie wäre es mit Christ 2: Resurrection oder Christ II - Judgement Day?
Nur so Ideen...

Apropos, ich habe die Passion immer noch nicht gesehen. Niemand in Stuttgart, der rein möchte? Melde Dich!

Markus Krötzsch ISWC 2022 keynote

A brilliant keynote by Markus Krötzsch for this year's ISWC.

"The era of standard semantics has ended"

Yes, yes! 100%! That idea was in the air for a long time, but Markus really captured it in clear and precise language.

This talk is a great birthday present for Wikidata's ten year anniversary tomorrow. The Wikidata community had over the last years defined numerous little pockets of semantics for various use cases, shared SPARQL queries to capture some of those, identified constraints and reasoning patterns and shared those. And Wikidata connecting to thousands of external knowledge bases and authorities, each with their own constraints - only feasible since we can, in a much more fine grained way, use the semantics we need for a given context. The same's true for the billions of Schema.org triples out there, and how they can be brought together.

The middle part of the talk goes into theory, but make sure to listen to the passionate summary at 59:40, where he emphasises shared understanding, that knowledge is human, and the importance of community.

"Why have people ever started to share ontologies? What made people collaborate in this way?" Because knowledge is human. Because knowledge is often more valuable when it is shared. The data available on the Web of linked data, including Wikidata, Data Commons, Schema.org, can be used in many, many ways. It provides a common foundation of knowledge that enables many things. We are far away from using it to its potential.

A remark on triples, because I am still thinking too much about them: yes to Markus's comments: "The world is not triples, but we make it triples. We break down the world into triples, but we don't know how to rebuild it. What people model should follow the technical format is wrong, it should be the other way around" (rough quotes)

At 1:17:56, Markus calls back our discussions of the Wikidata data model in 2012. I remember how he was strongly advocating for more standard semantics (as he says), and I was pushing for more flexible knowledge representations. It's great to see the synthesis in this talk.

May 2019 talks

I am honored to give the following three invited talks in the next few weeks:

The topics will all be on Wikidata, how the Wikipedias use it, and the Abstract Wikipedia idea.

Maybe the hottest conference ever

The Wikipedia Hacking Days are over. We have been visiting Siggraph, we had a tour through the MIT Media Lab, some of the people around were Brion Vibber (Wikimedia's CTO), Ward Cunningham (the guy who invented wikis), Dan Bricklin (the guy who invented spreadsheets), Aaron Swartz (a web wunderkind, he wrote the RSS specs at 14), Jimbo Wales (the guy who made Wikipedia happen), and many other people. We have been working at the One Laptop per Child offices, the office to easily the coolest project of the world.

During our stay at the Hacking Days, we had the chance to meet up with the local IBM Semantic Web dev staff and Elias Torres, who showed us the fabulous work they are doing right now on the Semantic Web technology stack (never before rapid application deployment was so rapid). And we also met up with the Simile project people, where we talked about connecting their stuff like Longwell and Timeline to the Semantic MediaWiki. We actually tried Timeline out on the ISWC2006 conference page, and the RDF worked out of the box, giving us a timeline of the workshop deadlines. Yay!

Today started Wikimania2006 at the Harvard Law School. was not only a keynote by Lawrence Lessig, as great as expected, but also our panel on the Semantic Wikipedia. We had an unexpected guest (who didn't get introduced, so most people didn't even realize he was there), Tim Berners-Lee, probably still jetlagged from a trip to Malaysia. The session was received well, and Brion said, that he sees us on the way of getting the extension into Wikipedia proper. Way cool. And we got bug reports from Sir Timbl again.

And there are still two days to go. If you're around and like to meet, drop a note.

Trust me — it all sounds like a dream to me.


Comments are still missing on this post.

Meat Loaf

"But it was long ago
And it was far away
Oh God, it seemed so very far
And if life is just a highway
Then the soul is just a car
And objects in the rear view mirror may appear closer than they are."

Bat out of Hell II: Back into Hell was the first album I really listened to, over and over again. Where I translated the songs to better understand them. Paradise by the Dashboard Light is just a fun song. He was in cult classic movies such as The Rocky Horror Picture Show, Fight Club, and Wayne's World.

Many of the words we should remember him for are by Jim Steinman, who died last year and wrote many of the lyrics that became famous as Meat Loaf's songs. Some of Meat Loaf's own words better not be remembered.

Rock in Peace, Meat Loaf! You have arrived at your destination.

Meeting opportunities

I read in an interview in Focus (German) with Andreas Weigend, he says that publishing his travel arrangements in his blog helped him meet interesting people and allow for unexpected opportunities. I actually noticed the same thing when I wrote about coming to Wikimania this summer. And those were great meetings!

So, now, here are the places I will be in the next weeks.

  • Oct 18-Oct 20, Madrid: SEKT meeting
  • Oct 22-Oct 26, Milton Keynes (passing through London): Talk at KMi Podium, Open University, on Semantic MediaWiki. There's a webcast! Subscribe, if you like.
  • Oct 30-Nov 3, Montpellier: ODBASE, and especially OntoContent. Having a talk there on Unit testing for ontologies.
  • Nov 5-Nov 13, Athens, Georgia: ISWC and OWLED
  • Nov 15-Nov 17, Ipswich: SEKT meeting
  • Nov 27-Dec 1, Vienna: Keynote at Semantics on Semantic Wikipedia
  • Dec 13-17, Ljubljana: SEKT meeting
  • Dec 30-Jan 10, Mumbai and Pune: the travel is private, but this doesn't mean at all we may not meet for work if you're around that part of the world

Just mail me if you'd like to meet.

Mehr Euromünzen

Seite ein wenig verschönert, aber das wird man wohl kaum bemerken. Genaueres wie immer in der Site history.

Übrigens, ich sammel immer noch Euros. Damit meine ich nicht, dass ich reich werden möchte - das sowieso - sondern ich meine, dass ich versuche, eine vollständige Sammlung der verschiedenen Euros aus allen Eurostaaten zusammenzubekommen. Bezüglich des Vatikans, San Marinos und Monacos habe ich das schon aufgegeben, aber von den restlichen fehlen mir nur noch vier (4) Stück. Also, Geldbeutel aufgemacht, nachgeschaut, oder Bekannte in den entsprechenden Gegenden aus dem Bett geklingelt, und schickt mir die mir fehlenden Stücke. Biiiiiiiittteeee! Ich versuche mich auch zu bedanken.Mir fehlen auch nur das luxemburger 5 ct-Stück, die finnischen 1 und 2 ct-Stücke und - ausgerechnet! - die portugisische 2 Euro-Münze. Mailt mich an, wenn ihr was habt.

Meine Arbeit

An was forsche ich eigentlich?
Zunächst, eingestellt bin ich am AIFB, dem Institut für Angewandte Informatik und formale Beschreibungssprachen, der Universität Karlsruhe.
Hier wird schon seit Jahren am Semantic Web geforscht, und das Institut hat sich bereits einen hervorragenden Namen hierbei gemacht.

Der bekannteste Verfechter des Semantic Webs dürfte unzweifelhaft Sir Tim Berners-Lee sein, der, noch gar nicht so lange her, das World Wide Web ins Rollen brachte.

Was nun aber ist das Semantic Web?
Inzwischen habe ich ein paar grobe Ideen, und in den kommenden Blog-Einträgen werde ich versuchen mich der Antwort zu nähern. Natürlich sollen aber auch weiterhin die sonstigen Themen von Nodix nicht kürzer kommen als bisher. Aber eben mit ein wenig semantischer Würze.

Meine Familie

Mitschnitt eines Gespräches zwischen meiner Mutter und Schwesterchen:
"Und sag, wo ist Dein Bruder?"
"Zur AOK und dann zur Polizei."
"Was!? Die AOK hat Samstags offen?"

Da kann man doch sehr leich einen falschen Eindruck erhalten, oder?

Meldung aus Turin

Diesmal nicht von der Essener Spielemesse, auch wenn ich dazu noch ein, zwei Sachen schreiben werde... Nein, ich bin in Turin. Ich besuche die FOIS 2004, eine Konferenz ueber formale Ontologien in der Informatik, der ich mit Spannung entgegensehe. Wer mich kennt, weiss, dass ich sowohl Informatik als auch Philosophie studierte, und umso spannender finde ich die Schnittstelle zwischen den beiden -- wie etwa hier.
Dazu waehrend dem Verlauf mehr.
Turin selbst ist insbesondere regnerisch. Und was mir auffiel: mein Zug vom Flughafen in die Stadt hatte satte 45 Minuten Verspaetung. Und das schien hier vollkommen gewoehnlich zu sein -- niemand aergerte sich auch nur! Die anderen Zuege hatten bis zu anderthalb Stunden Verspaetung, kein einziger schien puenktlich.

Allerdings: die Zuege fahren im Stunden- oder Halbstundentakt. Da stellt man sich die Frage, ob der Zug ueberhauipt noch als verspaetet angesehen wird, oder ob man ihn einfach als den naechsten Zug betrachtet?

Melodie zu Diadem aus Elfenhand

Wie vielleicht manche von Euch wissen, erschien letztes Jahr in dem Abenteuersammelband "Leicht verdientes Gold" mein DSA-Abenteuer "Ein Diadem von Elfenhand". Darin spielt eine bestimmte Melodie eine wichtige Rolle - und in letzter Zeit erhalte ich immer häufiger eMails, die micht fragen, wie die Melodie geht. Da meine Stimme die letzten paar Tage versagt hat, und ich ohnehin nicht vorhatte es jedem einzeln am Telefon vorzusingen, habe ich kurzerhand ein Midi erstellt, welches die Melodie abspielen kann. Es klingt zwar furchtbar, aber besser als nichts.

Milk consumption in China

Quiet disappointed by The Guardian. Here's a (rather) interesting article on the history of milk consumption in China. But the whole article is trying to paint how catastrophic this development might be: the Chinese are trying to triple their intake in milk! That means more cows! That's bad because cows fart us into a hot house!

The argumentation is solid - more cows are indeed problematic. But blaming it on milk consumption in China? Let's take a look at a few numbers omitted from the article, or stuffed into the very last paragraph.

  • On average, a European consumes six times as much milk as a Chinese. So, even if China achieves its goal and triples average milk consumption, they will drink only half as much as a European.
  • Europe has double the number of dairy cows than China has.
  • China is planning to increase their milk output by 300% but only increase resources for that by 30% according to the article. I have no idea how that works, but sounds like a great deal to me.
  • And why are we even talking about dairy cows? The number of beef cows in the US or in Europe each outnumber the dairy cows by a fair amount (unsurprisingly - a cow produces quite a lot of milk over a longer time, whereas its meat production is limited to a single event)
  • There are about 13 million dairy cows in China. The US have more than 94 million cattle, Brazil has more than 211 million, world wide it's more than 1.4 billion - but hey, it's the Chinese milk cows that are the problem.

Maybe the problem can be located more firmly in the consumption habits of people in the US and in Europe than the "unquenchable thirst of China".

The article is still interesting for a number of other reasons.

MinCardinality

More on the Unique Name Assumption (UNA), because Andrew answered on it, with further arguments. He quotes Paul: " The initial problem was cardinality and OWL Flight attempts to solve the problem with cardinality. Paul put it succinctly: "So what is the point of statements with the owl:minCardinality predicate? They can't ever be false, so they don't tell you anything! It's kind of like a belt and braces when your belt is unbreakable." "

Again I disagree, this time to Paul: the minimal cardinality axiom does make sense. For what, they ask - well, for saying that there is a minimal cardinality on this relation. Yeah, you are right: this is an axiom which hardly can lead to an inconsisten ontology. But so what? You nevertheless can cut down the number of possible models with it and get more information out of the ontology.

"I would agree - this was my main problem - how do you explain to Joe (and Andrew) that all his CDs are the same rather than different."

That's turning around the argument. If the reasoner would claim that all of Joes CDs are the same, he would be doing a grave mistake. But so would he if he would claim that all are different: the point is, he just doesn't know. Without having someone to state sameness or difference explicitly, well, you can't know.

"I did comment that the resolution, local unique names using AllDifferent, didn't actually seem to solve the problem well enough (without consideration for scalability for example)."

I am not sure why that should be. It seems that Andrew would be happy if there was a file-wide switch claiming "If I use different URIs here I mean different objects. This file makes the UNA." These files would easily be translated to standard OWL files, but there would be less clutter inside (actually, everything that would need to be done is adding an axiom of allDifferent with all the names of the file).

"I have a feeling that context is a better solution to this problem (that might just be my golden hammer though)."

I don't understand this one, maybe Andrew will elaborate a bit on this.

If you imagine an environment with axioms floating around, from repository to repository, being crawled, collected, filtered, mapped and combined, you must not make the Unique Name Assumption. If you remain in your own personal knowledge base, you can embrace UNA. And everything you need between is one more axiom.

Is it that bad?