Abstract: Techniques are described herein for automated assistants that search various alternative corpora for information. In various implementations, a method may include receiving, by an automated assistant via an input component of a first client device, a free form input, wherein the free form input includes a request for specific information; searching a general purpose corpus of online documents to obtain a first set of candidate response(s) to the request for specific information; searching a user-specific corpus of active document(s) to obtain a second set of candidate response(s) to the request for specific information; comparing the first and second sets of candidate responses; based on the comparing, selecting a given response to the request for specific information from the first or second set; and providing, by the automated assistant, output indicative of the given response.

Abstract: The present disclosure relates to user-selected metadata related to images captured by a camera of a client device. User-selected metadata may include contextual information and/or information provided by a user when the images are captured. In various implementations, a free form input may be received at a first client device of one or more client devices operated by a user. A task request may be recognized from the free form input, and it may be determined that the task request includes a request to store metadata related to one or more images captured by a camera of the first client device. The metadata may be selected based on content of the task request. The metadata may then be stored, e.g., in association with one or more images captured by the camera, in computer-readable media. The computer-readable media may be searchable by the metadata.

Abstract: Methods, apparatus, and computer readable media are described related to causing processing of sensor data to be performed in response to determining a request related to an environmental object that is likely captured by the sensor data. Some implementations further relate to determining whether the request is resolvable based on the processing of the sensor data. When it is determined that the request is not resolvable, a prompt is determined and provided as user interface output, where the prompt provides guidance on further input that will enable the request to be resolved. In those implementations, the further input (e.g., additional sensor data and/or the user interface input) received in response to the prompt can then be utilized to resolve the request.

Abstract: Contextual paste target prediction is used to predict one or more target applications for a paste action, and do so based upon a context associated with the content that has previously been selected and copied. The results of the prediction may be used to present to a user one or more user controls to enable the user to activate one or more predicted application, and in some instances, additionally configure a state of a predicted application to use the selected and copied content once activated. As such, upon completing a copy action, a user may, in some instances, be provided with an ability to quickly switch to an application into which the user was intending to paste the content. This can provide a simpler user interface in a device such as phones and tablet computers with limited display size and limited input device facilities. It can result in a paste operation into a different application with fewer steps than is possible conventionally.

Abstract: The present application discloses systems and methods for using probabilistic prioritization to assign human reviewers to review data stored in or indexed by an information system. Some embodiments include accessing an index of data items, where individual data items have a corresponding probability f of having a problem, a cost to review the data item, a penalty if a problem associated with the data item is not remedied, and a gain if a problem associated with the data item is remedied; identifying a subset of data items having a corresponding f that is greater than or equal to a decision threshold based on the data item's corresponding cost, penalty, and gain; and ranking at least a portion of the subset of data items based at least in part on their corresponding cost, f, and gain.