Abstract: In one embodiment, a method includes receiving a user request to automatically debug a natural-language understanding (NLU) model, accessing a plurality of predicted semantic representations generated by the NLU model, wherein the plurality of predicted semantic representations are associated with a plurality of dialog sessions, respectively, wherein each dialog session is between a user and an assistant xbot associated with the NLU model, generating a plurality of expected semantic representations associated with the plurality of dialog sessions based on an auto-correction model, wherein the auto-correction model is learned from dialog training samples generated based on active learning, identifying incorrect semantic representations of the predicted semantic representations based on a comparison between the predicted semantic representations and the expected semantic representations, and automatically correcting the incorrect semantic representations by replacing them with respective expected semantic repre

Abstract: In one embodiment, a method includes receiving a request to train a natural-language understanding (NLU) model for a new domain, accessing a context-free grammar associated with the new domain, wherein the context-free grammar defines production rules with respect to ontology tokens associated with the new domain and utterance tokens for generating natural-language strings in the new domain, generating utterance-frame pairs based on traversing a hierarchical grammar tree associated with the context-free grammar based on the production rules, wherein each utterance-frame pair comprises an utterance and a corresponding frame, wherein each frame comprises ontology tokens associated with the new domain and utterance tokens corresponding to one or more of the ontology tokens of the frame, and training the NLU model based on the utterance-frame pairs.

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: In one embodiment, a method includes receiving a user request to automatically debug a natural-language understanding (NLU) model, accessing a plurality of predicted semantic representations generated by the NLU model, wherein the plurality of predicted semantic representations are associated with a plurality of dialog sessions, respectively, wherein each dialog session is between a user and an assistant xbot associated with the NLU model, generating a plurality of expected semantic representations associated with the plurality of dialog sessions based on an auto-correction model, wherein the auto-correction model is learned from dialog training samples generated based on active learning, identifying incorrect semantic representations of the predicted semantic representations based on a comparison between the predicted semantic representations and the expected semantic representations, and automatically correcting the incorrect semantic representations by replacing them with respective expected semantic repre

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: A user's experience with internet content may be given semantic meaning based upon extracting features of the content and creating kind classifications from the features. Kind classifications may be used to enrich a user's experience with internet content by providing meaningful navigation and discovery of information. As provided herein, a data stream (e.g., HTML, audio, video, unstructured data, etc.) is received, and features (e.g., text, phrases, titles, paragraphs, image data, etc.) may be extracted from the data stream. Kind classifications may be created based upon the extracted features. For example, a shirt image kind classification may be created based upon a button image feature, a collar image feature, and a sleeve image feature. The user's experience may be enriched by a presentation of actions allowing the user to view similar shirts, purchase the shirt, and/or discover other information relating to the shirt, for example.

Abstract: The present starburst target expansion technique connects targets to peripheral screen space to produce reasonably sized tiles for all targets including those that are located inside of a cluster. The resulting layout is characterized by lines escaping from the cluster center. By providing targets located inside a cluster with access to empty screen space, the present starburst target expansion technique is able to assign screen space to targets that remain small if expanded using the traditional Voronoi approach. If used on a device with limited input accuracy, such as a pen-based tablet or a touch screen-based kiosk system, target expansion via the starburst target expansion technique can lead to substantial performance improvements.

Abstract: Shape recognition is performed based on determining whether one or more ink strokes is not part of a shape or a partial shape. Ink strokes are divided into segments and the segments analyzed employing a relative angular distance histogram. The histogram analysis yields stable, incremental, and discriminating featurization results. Neural networks may also be employed along with the histogram analysis to determine complete shapes from partial shape entries and autocomplete suggestions provided to users for conversion of the shape into a known object.

Abstract: A system and method for performing ink related operations in a tree-based presentation system is described. Ink-related programmatical interfaces may relate to interactions with a stroke object, a stroke collection object, and ink input elements.

Abstract: Upon detection of user input, a computing device (e.g., tablet PC, PDA, cellular device) may determine whether the input corresponds to a request to enhance elements of the user interface. In response to a positive determination, the computing device may magnify or otherwise modify the appearance of particular graphical elements of the interface to facilitate user interaction. The computing device identifies one or more graphical elements that are within a predefined proximity or area of the input location and displays an enlarged version of those elements to provide the user with a larger interaction area. Additionally, a computing device may clone (i.e., copy) the identified elements and enlarge the cloned elements at a specified region of the user interface. In another aspect, the computing device may magnify the entire area associated with the location of user input, rather than just the interactive elements of that predefined area.

Abstract: Methods of controlling the display and use of a UI element are disclosed. In an embodiment, the UI element may configured so that it initially maintains a topmost position but eventually allows other applications to assume the topmost position. In an embodiment, the display of the UI element may be adjusted in response to an input so that the UI element is not visible on the display. In an embodiment, the use of the UI element may allow for seamless dragging of the UI element even if the user inadvertently fails to make consistent contact with the touch-sensitive display while dragging the UI element.

Abstract: A system and process for ensuring the smooth flow of electronic ink is described. Dynamic rendering is give priority over other event handlers. Priority may be the use of one or more queues to order when events occur and may be performing dynamic rendering prior to other steps.

Abstract: A method for rejecting an unintentional palm touch is disclosed. In at least some embodiments, a touch is detected by a touch-sensitive surface associated with a display. Characteristics of the touch may be used to generate a set of parameters related to the touch. In an embodiment, firmware is used to determine a reliability value for the touch. The reliability value and the location of the touch is provided to a software module. The software module uses the reliability value and an activity context to determine a confidence level of the touch. In an embodiment, the confidence level may include an evaluation of changes in the reliability value over time. If the confidence level for the touch is too low, it may be rejected.

Abstract: A system and process for ensuring the smooth flow of electronic ink is described. Dynamic rendering is give priority over other event handlers. Priority may be the use of one or more queues to order when events occur and may be performing dynamic rendering prior to other steps.