Abstract: In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.

Abstract: In an approach to AI explaining for natural language processing, responsive to receiving an input text for a machine learning model, an output is generated from the machine learning model. A plurality of alteration techniques are applied to the input text to generate one or more alternate outputs, where each alternate output corresponds to an alteration technique. A variation rate of the alternate output is calculated for each alteration technique. A preferred technique of generating neighboring data of the input text is generated based on a comparison of the variation rate of the alternate output for each alteration technique.

Abstract: A computer device obtains a plurality of terms uttered during a recorded communication between a plurality of parties, identifying information for one or more of the plurality of parties, and an identification of which recorded terms were uttered by each of the one or more parties. The computer device transmits data identifying one or more of the recorded terms, the one or more recorded terms uttered by each party of the one or more parties to be displayed as associated with the party, and the recorded terms being selectable. In response to one of the recorded terms being selected, the computer device transmits data identifying one or more representative utterance times that the selected term was uttered by at least one of the one or more parties, the selected term to be displayed as associated with the one or more representative utterance times along a time axis.

Abstract: A computer device obtains a plurality of terms uttered during a recorded communication between a plurality of parties, identifying information for one or more of the plurality of parties, and an identification of which recorded terms were uttered by each of the one or more parties. The computer device transmits data identifying one or more of the recorded terms, the one or more recorded terms uttered by each party of the one or more parties to be displayed as associated with the party, and the recorded terms being selectable. In response to one of the recorded terms being selected, the computer device transmits data identifying one or more representative utterance times that the selected term was uttered by at least one of the one or more parties, the selected term to be displayed as associated with the one or more representative utterance times along a time axis.

Abstract: A computer-implemented method for supporting analysis based on a workflow, includes: obtaining a non-timeline-based workflow including a first process and a second process to that is executed after the first process; and outputting a timeline-based workflow including the first process arranged at a first position corresponding to a first time and the second process arranged at a second position corresponding to a second time after the first time.

Abstract: A computer-implemented method for supporting analysis based on a workflow, includes: obtaining a non-timeline-based workflow including a first process and a second process to that is executed after the first process; and outputting a timeline-based workflow including the first process arranged at a first position corresponding to a first time and the second process arranged at a second position corresponding to a second time after the first time.