Abstract: Creating visualizations from human readable data in electronic documents is provided. One or more facts may be parsed from an electronic document by a computing device. The one or more facts may consist of a human readable sentence. A search may then be performed for an icon based on the one or more facts. The computing device may then generate a data visualization, such as an infographic, which includes the one or more facts and the icon. The generated data visualization may then be displayed in the electronic document.

Abstract: User input identifying a selection of a textual portion of a document being displayed in a computer display region can be received. Identification of an entity indicated by the selection and text around the selection can be automatically requested. A determination of whether the identified entity is an entity type in a predetermined set of entity types can also be requested. Each entity type in the set can correspond to a display technique for displaying information about that entity type. The display technique for each entity type can be different and can include displaying one or more user interface items specific to the entity type. If the entity type is determined to be an entity type of the types in the set, then the information about the identified entity can be displayed according to the display technique for the determined entity type.

Abstract: User input identifying a selection of a textual portion of a document being displayed in a computer display region can be received. An identification of a meaning of the selection by analyzing context information around the selection can be automatically requested. A dataset about the identified meaning can be retrieved from a service. A selection of a visualization format from a plurality of available visualization formats can be automatically requested to represent the dataset. A visualization of the dataset in the selected visualization format can be automatically displayed. The visualization can represent at least a portion of the dataset.

Abstract: User input identifying a selection of a textual portion of a document (such as an e-reader document, a word processing document, etc.) being displayed in a first computer display region can be received. It can be automatically requested that one or more services identify a context-sensitive meaning of the selection by analyzing textual context information around the selection in the document. Additional information about the identified meaning of the selection can be automatically retrieved from a service. In response to receiving the user input, one or more representations of the information about the identified meaning can be displayed in a second computer display region while the document continues to be displayed in the first computer display region. The first and second display regions can be visible at the same time.