This paper presents enhancements to previous algorithms for the sequential extraction of complete non-redundant set of rules from a concept lattice. The aim of these enhancements i...
We propose a backoff model for phrasebased machine translation that translates unseen word forms in foreign-language text by hierarchical morphological abstractions at the word an...
In this paper we discuss algorithms for clustering words into classes from unlabelled text using unsupervised algorithms, based on distributional and morphological information. We...
This paper shows how the best data-driven dependency parsers available today [1] can be improved by learning from unlabeled data. We focus on German and Swedish and show that label...
We show the powerful sparse signal recovery approach FOCUSS is a convex-concave procedure. It follows a Newton-like decent direction by retaining the positive definite component ...