We introduce a framework, which we call Divide-by-2 (DB2), for extending support vector machines (SVM) to multi-class problems. DB2 offers an alternative to the standard one-again...
Selecting relevant features for Support Vector Machine (SVM) classifiers is important for a variety of reasons such as generalization performance, computational efficiency, and ...
We present an adaptation technique for statistical machine translation, which applies the well-known Bayesian learning paradigm for adapting the model parameters. Since state-of-t...
We present an on-line learning framework tailored towards real-time learning from observed user behavior in search engines and other information retrieval systems. In particular, ...
Abstract. There are many connections between graph mining and inductive logic programming (ILP), or more generally relational learning. Up till now these connections have mostly be...