| 摘要 |
An end user, by way of a submission interface, instructs an engine to select particular collections of documents to process. The engine processes all the text from within all the documents from within the selected collections. The result of the processing of such text is a distilled data set. Such distillate data set is accessed through APIs by a browser. Different views of the accessed distillate data set may be presented to the end user via the browser allowing them to more effectively assess the utility of the presented data and thereby responsively tune the presented data set with regard to their particular research task. One or more of such views may be used to create a new document from sentences, paragraphs, chapters or documents from the distillate data set that correspond to the one or more views for presentation to the end user.
|
