The absence of explicit word boundary delimiters, such as spaces, in Japanese texts causes all kinds of troubles for Japanese morphological analysis systems. Particularly, out-of-vocabulary words represent a very serious problem for the systems which rely on dictionary data to establish word boundaries. In this paper we present a solution for decompounding of katakana sequences (one of the main...

In this paper, we present CONTRAlign, an extensible and fully automatic framework for parameter learning and protein pairwise sequence alignment using pair conditional random fields. When learning a substitution matrix and gap penalties from as few as 20 example alignments, CONTRAlign achieves alignment accuracies competitive with available modern tools. As confirmed by rigorous cross-validated...