Abstract: A social network model, based on data relevant to a user, is used for semantic processing to enable improved entity recognition among text accessed by the user. An entity extraction module of the server, with reference to a general training corpus, general gazetteers, user-specific gazetteers, and entity models, parses text to identify entities. The entities may be, for example, people, organizations, or locations. A social network module of the server builds the social network model implicit in the data accessed by the user. The social network model includes the relationships between entities and an indication of the strength of each relationship. The social network module is also used to disambiguate names and unify entities based on the social network model.

Abstract: A user interface for a mobile device allows users to interact across applications with information relevant to known people, organizations, or locations, referred to herein as “recognized entities.” Every type of recognized entity has associated action options that populate a node menu for that type. The node menu options are selectable, for example, through a touchscreen interface, to rapidly execute the associated action. In another embodiment, a plurality of data windows, referred to as “spinners,” are viewed simultaneously on one display. Each spinner is a view of one or more data objects provided that are distinguished from one another by data type, context, parsing or sorting algorithms, or user interaction with this data. The spinners respond to user actions, to new information from the server, or external events by automatically visibly scrolling the data displayed in the spinner windows.

Abstract: A user interface for a mobile device allows users to interact across applications with information relevant to known people, organizations, or locations, referred to herein as “recognized entities.” Every type of recognized entity has associated action options that populate a node menu for that type. The node menu options are selectable, for example, through a touchscreen interface, to rapidly execute the associated action. In another embodiment, a plurality of data windows, referred to as “spinners,” are viewed simultaneously on one display. Each spinner is a view of one or more data objects provided that are distinguished from one another by data type, context, parsing or sorting algorithms, or user interaction with this data. The spinners respond to user actions, to new information from the server, or external events by automatically visibly scrolling the data displayed in the spinner windows.

Abstract: A social network model, based on data relevant to a user, is used for semantic processing to enable improved entity recognition among text accessed by the user. An entity extraction module of the server, with reference to a general training corpus, general gazetteers, user-specific gazetteers, and entity models, parses text to identify entities. The entities may be, for example, people, organizations, or locations. A social network module of the server builds the social network model implicit in the data accessed by the user. The social network model includes the relationships between entities and an indication of the strength of each relationship. The social network module is also used to disambiguate names and unify entities based on the social network model.