Abstract: Computer-implemented methods for selecting displayed content are provided. In one aspect, a method includes receiving a selection request for content displayed on a device, and predicting, while receiving the selection request, content intended to be selected based on at least one of a visual cue, historic cue, semantic term, or user habit. The method also includes selecting the predicted content displayed on the device. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on a visibility of content within a viewport of a device. In one aspect, a method includes receiving information on content currently loaded for display on a device. The information includes an indication of whether at least one portion of the content has entered a viewport of the device. The method also includes identifying, based on the content, at least one suggestion to provide for display with the search field, wherein the at least one suggestion is weighted based on whether a portion of the content referring to at least one suggestion has entered the viewport of the device, and providing the at least one suggestion for display with a display of a search field on the device. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for proposing actions to a user to select based on the user's predicted purpose for selecting content are provided. In one aspect, a method includes receiving an identifier of a referent entity associated with user-selectable content, identifying, based on a prediction of a purpose in selecting the content, at least one action to be executed that is associated with the entity, and providing, for display, at least one identifier of the at least one action to the device for selection by a user. Systems, graphical user interfaces, and machine-readable media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for proposing actions to a user to select based on the user's predicted purpose for selecting content are provided. In one aspect, a method includes receiving an identifier of a referent entity associated with user-selectable content, identifying, based on a prediction of a purpose in selecting the content, at least one action to be executed that is associated with the entity, and providing, for display, at least one identifier of the at least one action to the device for selection by a user. Systems, graphical user interfaces, and machine-readable media are also provided.

Abstract: Computer-implemented methods for proposing actions to a user to select based on the user's predicted purpose for selecting content are provided. In one aspect, a method includes receiving an identifier of a referent entity associated with user-selectable content, identifying, based on a prediction of a purpose in selecting the content, at least one action to be executed that is associated with the entity, and providing, for display, at least one identifier of the at least one action to the device for selection by a user. Systems, graphical user interfaces, and machine-readable media are also provided.

Abstract: Computer-implemented methods for refining a selection of content using touch input are provided. In one aspect, a method includes receiving a first touch input from a user for selecting content displayed on a device, and providing, for display, a visual indicator of the content that has been selected. The method also includes receiving a second touch input indicating a refinement to the selection of the content. The refinement of the selection of the content is based on at least one referent entity identified with the selected content. Systems and machine-readable media are also provided.

Abstract: Computer-implemented methods for selecting displayed content are provided. In one aspect, a method includes receiving a selection request for content displayed on a device, and predicting, while receiving the selection request, content intended to be selected based on at least one of a visual cue, historic cue, semantic term, or user habit. The method also includes selecting the predicted content displayed on the device. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for updating actions for a user to select based on the user's predicted purpose for selecting content are provided. In one aspect, a method includes receiving content selected by a user from a device, and providing, for display, at least one action to be executed that is associated with a referent entity identified from the selected content. The method also includes receiving an indication that a performance of the action was abandoned by the user, and updating the association of the action with the referent entity based on the indication that the performance of the action was abandoned by the user. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on a visibility of content within a viewport of a device. In one aspect, a method includes receiving information on content currently loaded for display on a device. The information includes an indication of whether at least one portion of the content has entered a viewport of the device. The method also includes identifying, based on the content, at least one suggestion to provide for display with the search field, wherein the at least one suggestion is weighted based on whether a portion of the content referring to at least one suggestion has entered the viewport of the device, and providing the at least one suggestion for display with a display of a search field on the device. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for selecting displayed content are provided. In one aspect, a method includes receiving, at a starting point, a selection request for content displayed on a device, and predicting, while receiving the selection request, a shape and an ending point of the selection request based on the starting point. The method also includes selecting content displayed on the device based on the starting point, the predicted shape, and the predicted ending point. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for proposing actions to a user to select based on the value of the actions to the user are provided. In one aspect, a method includes receiving content selected by a user from a device, and identifying a plurality of actions to be executed that are associated with a referent entity identified from the selected content, wherein each action has an associated value to the user. The method also includes providing, for display, an identifier of each of at least a subset of the actions based on their associated values. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for providing suggestions for a search based on previously viewed content are provided. In one aspect, a method includes receiving information on previously viewed content, and receiving a request to enter a query into a search field subsequent to receiving the information on the previously viewed content. The method also includes identifying, based on the content, at least one entity referred to in the content, and providing an identifier of the at least one entity for display with the search field. Systems and machine-readable storage media are also provided.

Abstract: Computer-implemented methods for refining a selection of content using touch input are provided. In one aspect, a method includes receiving a first touch input from a user for selecting content displayed on a device, providing, for display, a visual indicator of the content that has been selected, and receiving a second touch input indicating a refinement to the selection of the content. The refinement of the selection of the content is based on at least one referent entity identified with the selected content. Systems and machine-readable media are also provided.

Abstract: Computer-implemented methods for identifying a requested action using a geometric input are provided. In one aspect, a method includes receiving a geometric pattern input associated with user-selectable content displayed on the device, and receiving an identifier of a referent entity, the referent entity selected based on the geometric pattern input from a list of suggested entities identified from user-selectable content displayed on the device. The method also includes identifying, based on a shape of the geometric pattern input, at least one action to be executed that is associated with the referent entity based on the shape of the geometric pattern input, and providing an identifier of the at least one identified action to the device for selection. Systems, graphical user interfaces, and machine-readable media are also provided.

Abstract: Computer-implemented methods for identifying an entity based on selected content are provided. In one aspect, a method includes identifying a referent entity, from a list of entities, based on user-selectable content of a file and a context in which the user-selectable content is selected from the file by a user, and providing an identification of the entity to a user device. Systems, graphical user interfaces, and machine-readable media are also provided.

Abstract: A facility for processing a request for information about a specified item is described. The facility receives the request from an originator. In response to receiving the request, the facility generates a response to the request that contains information about the specified item. The facility also determines a current level of availability of the specified item, and, based upon this determined level of availability, determines, for each of a number of ordering actions, whether the ordering action is currently available for the specified item. For each ordering action determined to be currently available for the specified item, the facility augments the generated response by adding a control for performing the ordering action. The facility sends the augmented response to the originator of the request.