Interactive concept editing in computer-human interactive learning

A method of interactively generating an updated representation of a first concept for training a classifier, the method comprising:

• presenting a user interface for generating a representation of the first concept by associating, to the first concept, a list of phrases that are specific examples of the first concept;
• providing, via the user interface, an input field that receives a first input comprising a plurality of characters of text that form at least one specific example of the first concept;
• generating a generalized concept determined at least in part from the first input, the generalized concept comprising a broader concept that encompasses the at least one specific example of the first concept;
• generating, based on the classifier, a set of phrases that are each a specific example of the generalized concept;
• providing, via the user interface, a first field that displays the set of phrases, that are each a specific example, as suggested phrases that are each selectable and collectively selectable for inclusion as specific examples of the first concept;
• receiving a second input indicative of a selection of at least one suggested phrase of the suggested phrases;
• providing, via the user interface, a second field that displays (1) the list of phrases that are specific examples of the first concept and (2) the at least one suggested phrase of the second input;
• saving (1) the list of phrases that are specific examples of the first concept and (2) the at least one suggested phrase of the second input as the updated representation of the first concept, wherein the classifier comprises a neural network that is trained based on a first machine learning feature indicating the updated representation that comprises (1) the list of phrases that are specific examples of the first concept and (2) the at least one suggested phrase of the second input;
• and
• generating, by the trained classifier, subsequent suggested words based on the updated representation, the subsequent suggested words comprising words that are specific examples of the broader concept.

A system for providing a user interface for interactively editing a machine-learning feature used in association with a classifier, the system comprising:

• one or more memory devices;
• and
• one or more processors configured to:
• cause presentation of the user interface adapted to generate a representation of a first concept by associating, to the first concept, a list of phrases that are specific examples of the first concept;
• provide, via the user interface, an input field that receives a first input comprising a plurality of characters of text that form at least one specific example of the first concept;
• generate a generalized concept determined at least in part from the first input, the generalized concept comprising a broader concept that encompasses the at least one specific example of the first concept;
• generate, based on the classifier, a set of phrases that are each a specific example of the generalized concept;
• provide, via the user interface, a first field that displays the set of phrases, that are each a specific example, as suggested phrases that are each selectable and collectively selectable for inclusion as specific examples of the first concept;
• receive a second input indicative of a selection of at least one suggested phrase of the suggested phrases;
• provide, via the user interface, a second field that displays (1) the list of phrases that are specific examples of the first concept and (2) the at least one suggested phrase of the second input;
• save (1) the list of phrases that are specific examples of the first concept and (2) the at least one suggested phrase of the second input as an updated representation of the first concept, wherein the classifier comprises a neural network that is trained based on a first machine learning feature indicating the updated representation that comprises (1) the list of phrases that are specific examples of the first concept and (2) the at least one suggested phrase of the second input;
• and
• generate, by the trained classifier, subsequent suggested words based on the updated representation, the subsequent suggested words comprising words that are specific examples of the broader concept.