Validation, rejection, and modification of automatically generated document annotations
AssigneeMicrosoft Corporation
InventorsLucretia Henrica Vanderwende, Oscar Gerardo Naim, Krist Wongsuphasawat
Life of this patent
Estimating the term…
Abstract
A mixed-initiative annotation framework is described herein. A document that includes several sentences is presented to a user, and an extractor module analyzes at least one sentence and automatically extracts a subject, predicate, object triple therefrom. The subject, predicate, object triple is displayed in graphical relation with the sentence as a proposed annotation to the sentence. Graphical options are presented to the user that allow the user to accept the proposed annotation, reject the proposed annotation, or modify the proposed annotation.
Claims20
A method, comprising:
- causing a processor in a computing device to search for content in a document that corresponds to predefined criteria;
- locating a portion of the document that corresponds to the predefined criteria based at least in part upon the processor searching for content in the document that corresponds to the predefined criteria;
- extracting a tuple of words or phrases from the portion of the document, wherein the tuple of words or phrases comprises an ordered set of words or phrases, wherein the ordered set of words or phrases comprises a first word or phrase, a second word or phrase, and a third word or phrase that relates the first word or phrase to the second word or phrase;
- causing the tuple to be displayed on a display screen corresponding to the computing device as a proposed annotation to the document;
- and
- causing a first user-selectable graphical object to be displayed on the display screen together with the proposed annotation, wherein selection of the first graphical object by the user causes the proposed annotation to be one of validated, rejected, or modified.
A system comprising a plurality of components that are executable by a processor, the plurality of components comprising:
- a document display component that causes a document selected by the user to be displayed to the user on a display screen of a computing device, wherein the document comprises a plurality of portions;
- a receiver component that receives a selection from the user of a portion of the document from amongst the plurality of portions;
- an extractor component that, responsive to the receiver component receiving the selection from the user of the portion of the document, automatically extracts a tuple from the portion of the document, wherein the tuple comprises a first word or phrase, a second word or phrase, and a third word or phrase that relates the first word or phrase to the second word or phrase, wherein subsequent to the extractor component automatically extracting the tuple from the portion of the document, the document display component displays the tuple to the user on the display screen of the computing device;
- and
- an option presenter component that causes a plurality of graphical objects to be displayed to the user together with the tuple, wherein the plurality of graphical objects correspond to validation of the tuple, rejection of the tuple, and modification of the tuple.
A computer-readable medium comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:
- responsive to input from a user, analyzing at least one sentence in a document that is being displayed to the user by way of a word processing application that is executing on a computing device that comprises the processor;
- automatically generating a tuple based at least in part upon the analyzing of the at least one sentence in the document, wherein the tuple comprises a subject, object, predicate triple;
- causing the tuple to be displayed on a display screen of the computing device in graphical relation to the at least one sentence;
- and
- causing a first graphical object, a second graphical object, and a third graphical object to be displayed on the computing device in graphical relation with the tuple, wherein user selection of the first graphical object indicates user-validation of the tuple, wherein user selection of the second graphical object indicates user-rejection of the tuple, and wherein user selection of the third graphical object indicates that the user wishes to modify at least a portion of the tuple.
Dependencies are inferred from the claim text.