Abstract: Systems and methods for providing an autofill user interface at a computing device are provided. In some aspects, a page is presented at the computing device, the page including one or more input boxes for entering input responsive to one or more prompts. One or more autofill suggestions for a first input box from the one or more input boxes are presented, where the one or more autofill suggestions are presented in a position overlaying the page, and where the page does not include the one or more autofill suggestions.

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: A server system hosts a plurality of conversations, each having an identified set of participants. For a respective conversation, the server accesses the conversation in which a user is a participant. The server obtains a conversation profile for the conversation, the conversation profile based on information including content of the conversation and user-specific term weights for at least a plurality of terms in the content of the conversation. The server accesses a plurality of entity profiles that are based on content and/or structure in other conversations in which the user is a participant. The server compares at least a subset of the entity profiles to the conversation profile to identify a set of entities having entity profiles that best match the conversation profile, generates a suggestion for the user including a suggested entity from the identified set of entities; and sends the suggestion to the client system for display to the user.

Abstract: A server system hosts a plurality of conversations, each having an identified set of participants. For a respective conversation, the server accesses the conversation in which a user is a participant. The server obtains a conversation profile for the conversation, the conversation profile based on information including content of the conversation and user-specific term weights for at least a plurality of terms in the content of the conversation. The server accesses a plurality of entity profiles that are based on content and/or structure in other conversations in which the user is a participant. The server compares at least a subset of the entity profiles to the conversation profile to identify a set of entities having entity profiles that best match the conversation profile, generates a suggestion for the user including a suggested entity from the identified set of entities; and sends the suggestion to the client system for display to the user.

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 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 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: A server system hosts a plurality of conversations, each having an identified set of participants. For a respective conversation, the server accesses the conversation in which a user is a participant. The server obtains a conversation profile for the conversation, the conversation profile based on information including content of the conversation and user-specific term weights for at least a plurality of terms in the content of the conversation. The server accesses a plurality of entity profiles that are based on content and/or structure in other conversations in which the user is a participant. The server compares at least a subset of the entity profiles to the conversation profile to identify a set of entities having entity profiles that best match the conversation profile, generates a suggestion for the user including a suggested entity from the identified set of entities; and sends the suggestion to the client system for display to the user.

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 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.