Abstract: The present disclosure relates to systems and methods for discovering relatedness between entities from a corpora of information by automatically extracting attributes from the plurality of heterogeneous entities in a graph. A standardized representation of the extracted attributes from the plurality of heterogeneous entities are propagated across the graph and these propagated attributes are used to find a degree to which the plurality of heterogeneous entities are associated with the extracted attributes. The degree to which the plurality of heterogeneous entities are associated with the extracted attributes is used to create a representation space illustrating a level of relatedness of an entity to another entity of the plurality of heterogeneous entities.

Abstract: A head mounted display device provides offset adjustments for gaze points provided by an eye tracking component. In a model generation phase, heuristics are used to estimate a gaze point of the user based on the gaze point provided by the eye tracking component and features that are visible in the field of view of the user. The features may include objects, edges, faces, and text. If the estimated gaze point is different than the gaze point that was provided by the eye tracking component, the difference is used to train a model along with a confidence value that reflects the strength of the estimated gaze point. In an adjustment phase, when the user is using an application that relies on the eye tracking component, the generated model is used to determine offsets to adjust the gaze points that are provided by the eye tracking component.

Abstract: The systems and techniques described herein implement an improved gaze-based on-screen keyboard that provide dynamically variable dwell times to increase throughput and reduce errors. Utilizing a language model, the probability that each key of the on-screen keyboard will be the subsequential key can be determined, and based at least in part on this determined probability, a dwell time can be assigned to each key. When used as an iterative process, a minimum dwell time may be gradually reduced as confidence in the subsequential key increases to provide a cascading minimum dwell time.