Abstract: A method includes identifying images associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes for each of the images, determining one or more labels, wherein the one or more labels are based on at least one of metadata and a primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to corresponding images. The method also includes interacting with the user to obtain identifying information that is used to categorize one or more of the images.

Abstract: A computing device may receive a communication sent from an external computing device. At least one processor of the computing device may determine, using an on-device machine-trained model and based at least in part on the communication, one or more candidate responses to the communication. The at least one processor may receive an indication of a user input that selects a candidate response from the one or more candidate responses. Responsive to receiving the indication of the user input that selects the candidate response, the at least one processor may send the candidate response to the external computing device.

Abstract: Implementations relate to automatic response suggestions based on images received in messaging applications. In some implementations, a computer-executed method includes detecting a first image included within a first message received at a second device over a communication network from a first device of a first user, and programmatically analyzing the first image to extract a first image content. The method includes retrieving a first semantic concept associated with the first image content, programmatically generating a suggested response to the first message based on the first semantic concept, and transmitting instructions causing rendering of the suggested response in the messaging application as a suggestion to a second user of the second device.

Abstract: A method includes identifying images associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes for each of the images, determining one or more labels, wherein the one or more labels are based on at least one of metadata and a primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to corresponding images. The method also includes interacting with the user to obtain identifying information that is used to categorize one or more of the images.

Abstract: Systems and methods for adding labels to a graph are disclosed. One system includes a plurality of computing devices including processors and memory storing an input graph generated based on a source data set, where an edge represents a similarity measure between two nodes in the input graph, the input graph being distributed across the plurality of computing devices, and some of the nodes are seed nodes associated with one or more training labels from a set of labels, each training label having an associated original weight. The memory may also store instructions that, when executed by the processors, cause the plurality of distributed computing devices to propagate the training labels through the input graph using a sparsity approximation for label propagation, resulting in learned weights for respective node and label pairs, and automatically update the source data set using node and label pairs selected based on the learned weights.

Abstract: A computing device may generate, a graph that includes a plurality of nodes, wherein the plurality of nodes includes a plurality of entity nodes representing a plurality of entities and a plurality of feature nodes representing a plurality of features, and wherein each of the plurality of entity nodes is connected in the graph to one or more of the plurality of feature nodes. The computing device may perform label propagation to associate a distribution of labels with each of the plurality of nodes. The computing device may be configured to receive an indication of at least one of a feature of interest or an entity of interest. The computing device may further be configured to output an indication of one or more related entities that are related to the feature of interest or the entity of interest.

Abstract: A method includes identifying an image associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes determining one or more labels for the image, where the one or more labels are based on at least one of metadata, a primary annotation, and a secondary annotation and the secondary annotation is generated by performing label expansion on at least one of the metadata and the primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to the image.

Abstract: A method includes identifying images associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes for each of the images, determining one or more labels, wherein the one or more labels are based on at least one of metadata and a primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to corresponding images. The method also includes interacting with the user to obtain identifying information that is used to categorize one or more of the images.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for classifying, or “labeling,” documents such as emails en masse based on association with a cluster/template. In various implementations, a corpus of documents may be grouped into a plurality of disjoint clusters of documents based on one or more shared content attributes. A classification distribution associated with a first cluster of the plurality of clusters may be determined based on classifications assigned to individual documents of the first cluster. A classification distribution associated with a second cluster of the plurality of clusters may then be determined based at least in part on the classification distribution associated with the first cluster and a relationship between the first and second clusters.

Abstract: Embodiments are directed towards providing word-by-word message completion for an incomplete response message, wherein the response message is composed in response to a received stimulus message. The message completion is based on a Response Completion Model (RCM) that may model both the language used in the incomplete response message and the contextual information in the received stimulus message. The RCM may be determined based on conversational stimulus-response data including stimulus-response message pairs. The RCM may be a mixture model and include a generic response language model based on an N-gram model, a Stimulus Model based on a Selection Model or a Topic. Model, and a mixture parameter. In some embodiments, at least one candidate next word for the incomplete response message is determined based on the RCM. The at least one candidate next word may be selected and included in the incomplete response message. A complete response message may be generated and provided to a user.

Abstract: Methods and apparatus related to identifying a category for a task that is associated with a user and populating annotation fields related to the task based on the category of the task. The task and populated annotation fields may be provided for use by one or more application to provide a task completion step to the user. In some implementations, the category may be identified based on input from the user, documents of the user, and/or data that are associated with the user. In some implementations, a completion step for the task may be suggested to the user by an application that accesses the task and populated annotated information. In some implementations, multiple applications may suggest different completion steps to the user for the same task.

Abstract: Methods and apparatus related to providing one or more completion step suggestions for a task that is associated with a user. In some implementations, the completion step suggestions may be provided to the user based on the satisfaction of a trigger condition. In some implementations, a trigger condition may be based on a user geographic location. In some implementations, a trigger condition may be based on an action of the user. In some implementations, a trigger condition may be based on a time when the associated task may be completed.

Abstract: Methods and apparatus related to providing one or more completion step suggestions for a task that is associated with a user. In some implementations, the completion step suggestions may be provided to the user based on the satisfaction of a trigger condition. In some implementations, a trigger condition may be based on a user geographic location. In some implementations, a trigger condition may be based on an action of the user. In some implementations, a trigger condition may be based on a time when the associated task may be completed.

Abstract: Methods and apparatus related to providing one or more completion step suggestions for a task that is associated with a user. In some implementations, the completion step suggestions may be provided to the user based on the satisfaction of a trigger condition. In some implementations, a trigger condition may be based on a user geographic location. In some implementations, a trigger condition may be based on an action of the user. In some implementations, a trigger condition may be based on a time when the associated task may be completed.

Abstract: Methods and apparatus related to receiving user task information indicative of an intended action of a user, determining additional information related to completion of the intended action, determining a completion step for the intended action based on the additional information, and providing the completion step to the user. The user task information may be received from a first source and the additional information may be determined from one or more additional sources that are distinct from the first source. Additional sources may include, for example, user data associated with the user and/or one or more non-user specific databases such as an entity database. Whether a completion step is provided to a user may be dependent on one or more factors such as, for example, the source of the user task information, the source of the additional information, and/or a trigger associated with the completion step.

Abstract: Embodiments are directed towards providing word-by-word message completion for an incomplete response message, wherein the response message is composed in response to a received stimulus message. The message completion is based on a Response Completion Model (RCM) that may model both the language used in the incomplete response message and the contextual information in the received stimulus message. The RCM may be determined based on conversational stimulus-response data including stimulus-response message pairs. The RCM may be a mixture model and include a generic response language model based on an N-gram model, a Stimulus Model based on a Selection Model or a Topic. Model, and a mixture parameter. In some embodiments, at least one candidate next word for the incomplete response message is determined based on the RCM. The at least one candidate next word may be selected and included in the incomplete response message. A complete response message may be generated and provided to a user.

Abstract: Automatic generation of bid phrases for online advertising comprising storing a computer code representation of a landing page for use with a language model and a translation model (with a parallel corpus) to produce a set of candidate bid phrases that probabilistically correspond to the landing page, and/or to web search phrases. Operations include extracting a set of raw candidate bid phrases from a landing page, generating a set of translated candidate bid phrases using a parallel corpus in conjunction with the raw candidate bid phrases. In order to score and/or reduce the number of candidate bid phrases, a translation table is used to capture the probability that a bid phrase from the raw bid phrases is generated from a bid phrase from the set of translated candidate bid phrases. Scoring and ranking operations reduce the translated candidate bid phrases to just those most relevant to the landing page inputs.