Microsoft Corporation
Context-sensitive salient keyword unit surfacing for multi-language survey comments

Abstract:

Computer-based implementations of context-sensitive salient keyword unit surfacing for multi-language comments are disclosed. A set of target keyword units in a target written language are caused by a computing system to be presented in a graphical user interface such as, for example, as part of a tag cloud or the like. The set of target keyword units are determined by the system by a context-sensitive mapping of a set of source keyword units in an intermediate written language to the set of target keyword units. The context sensitive mapping is constructed based on in-context machine translation of survey comments in the target language to the intermediate language and then identifying translation keyword unit pairs in the target language survey comments and the translated survey comments that represent a mapping of the in-context translation of a keyword unit in the target language to a keyword unit in the intermediate language.