Brito, EduardoEduardoBritoGeorgiev, BogdanBogdanGeorgievDomingo-Fernández, DanielDanielDomingo-FernándezHoyt, Charles TapleyCharles TapleyHoytBauckhage, ChristianChristianBauckhage2022-03-142022-03-142019https://publica.fraunhofer.de/handle/publica/4054702-s2.0-85073194141We present a general framework, RatVec, for learning vector representations of non-numeric entities based on domain-specific similarity functions interpreted as rational kernels. We show competitive performance using k-nearest neighbors in the protein family classification task and in Dutch spelling correction. To promote re-usability and extensibility, we have made our code and pre-trained models available athttps://github.com/ratvec.enrepresentation learningKernel Principal Component Analysisbioinformaticnatural language processing003005006629005006518conference paper