How would you explain Bill Gates to a German? He is associated with founding a company in the United States, so perhaps the German founder Carl Benz could stand in for Gates in those contexts. This type of translation is called adaptation in the tran
slation community. Until now, this task has not been done computationally. Automatic adaptation could be used in natural language processing for machine translation and indirectly for generating new question answering datasets and education. We propose two automatic methods and compare them to human results for this novel NLP task. First, a structured knowledge base adapts named entities using their shared properties. Second, vector-arithmetic and orthogonal embedding mappings methods identify better candidates, but at the expense of interpretable features. We evaluate our methods through a new dataset of human adaptations.
This piece of research endeavours to explain why translator's competence is not
homogeneously distributed among linguistically acculturated members of society. It
transpires that the cross-cultural communication skills possessed by a translator are
not
often born or merely characteristics of his natural ability. Professional translation is an
evolved natural translation. Undoubtedly, it is training, deepened expertise, and constant
upgraded and updated cognizance of the technicalities and strategies of translation that
qualify a translator to overcome the ever arising problems of translation. The cognitive
activity of translator's communicative competence underlies his professionalism
concerning the issues of invisibility, interference, creative restructuring process of
problem-solving and decision-making. Quite contrasted to translator as transmitter,
accumulative malleable communicative competence creates the translator who is a genuine
cultural mediator.
