I See Dead Code

Q: “How many constituent trees fit on a single A0 poster in style?” A: “886”

[Read more →]

My Master thesis “Integration of Light-weight Semantics into a Syntax Query Formalism” is available from the SALSA project pages. Abstract In the Computational Linguistics community, much work is put into the creation of large, high-quality linguistic resources, often with complex annotation. In order to make these resources accessible to nontechnical audiences, formalisms for searching and [...]

[Read more →]

Some participants of this semester’s „Computational Linguistics” course (which is a code word for „10 different lecturers guide you through the wonderful world of algorithms and theoretical foundations of CoLi”) obviously lack a life and willfully extended their own homework assignment, writing small toolkits for finite state automata. Surprisingly, all those toolkits were written in [...]

[Read more →]

Bewertung der Übersetzung von Satzfragmenten, gegeben: „Sporty Spice (Melanie Chisholm)” Sportliches Gewürz (Melanie Chisholm) sportliches Spice (Melanie Chisholm) Die Fehler oben sind vielleicht lustig, aber erwartbar. Erstaunlich ist eigentlich, dass eines der Systeme die korrekte Übersetzung angibt. Andererseits wurde das System wahrscheinlich einfach nur auf Texten von Klatschseiten trainiert.

[Read more →]

For one of the exercises, we had to implement the EM algorithm for Gaussian Mixture Models. I’ve spent a considerable amount of time on my solutions, either because I wanted to learn a new language (Scala version) or I wanted to not forgot an old one (C++ version), so I don’t want the code simply [...]

[Read more →]

Go to Jason Eisner’s homepage, please don’t come back to complain. Just to make it more geeky by nitpicking: if you are OOM, or have a segfault, you most likely won’t be able to finish your song.

[Read more →]

It’s only a couple of months late, but we’ve just released a new version of the Stockholm TreeAligner to an awed audience. This release features the prototype implementations of TIGERSearch and alignment queries, which will be perfected in the next release, due in March 2008. For those who are wondering what kind of code name [...]

[Read more →]

Es ist soweit, und die ganze Welt der Baumdatenbanken bekommt einen Geschmack vom Stockholm TreeAligner. Joakim wird morgen ein Poster über das „Gamla Stan”-Release von STA präsentieren (Paper). Nachdem das Release nur ein paar Monate verspätet war, machen wir uns auch gerade daran, die technische Basis mit ein paar gezielten geradezurücken. Die Hauptattraktionen für das [...]

[Read more →]