Abstract: A user using a messaging application may be in conversations with multiple people and may inadvertently send a message intended for a first person to a second person. The user may be warned before making such mistakes by processing the text of an entered message and/or the text of the conversations with a mathematical model. A match score may be computed that indicates the match between the entered message and the conversation in which it was entered. Where the match score indicates a possible mistake, a warning may be presented to the user. In some implementations, a match score may be computed using a conversation encoding vector and a message encoding vector. In some implementations, a match score may be computed by processing a sequence of tokens for the conversation and the entered message that includes special token separators.

Abstract: A speech processing model may be trained using pseudo tokens. Training a speech processing model with pseudo tokens may allow for training with a smaller amount of labeled training data and accordingly lower costs. A set of pseudo tokens may be determined by computing feature vectors from unlabeled training data, clustering the feature vectors, and performing token compression using the clustered feature vectors. A first speech processing model may be trained using unlabeled training data by determining sequences of pseudo tokens corresponding to the unlabeled training data. A second speech processing model may be initialized using the first speech processing model and then trained using labeled training data. The second speech processing model may then be deployed to a speech processing application.

Abstract: A user using a messaging application may be in conversations with multiple people and may inadvertently send a message intended for a first person to a second person. The user may be warned before making such mistakes by processing the text of an entered message and/or the text of the conversations with a mathematical model. A match score may be computed that indicates the match between the entered message and the conversation in which it was entered. Where the match score indicates a possible mistake, a warning may be presented to the user. In some implementations, a match score may be computed using a conversation encoding vector and a message encoding vector. In some implementations, a match score may be computed by processing a sequence of tokens for the conversation and the entered message that includes special token separators.

Abstract: For any application that processes speech, improving the quality of the feature vectors may improve the quality of the speech application. The quality of feature vectors may be improved by modifying a neural network architecture for computing feature vectors to allocate computational resources where they are more effective for learning and computing the feature vectors. Contextual feature vectors may be computed from feature vectors by using a parameterized downsampling operation that decreases a vector sequence rate, processing the downsampled vectors with a neural network, and using a parameterized upsampling operation that increases a vector sequence rate. For example, parameterized downsampling may decrease a vector sequence rate by a factor of two, a neural may require fewer computational resources since it operates with a lower vector sequence rate, and parameterized upsampling may then increase the vector sequence rate by a factor of two.

Abstract: A message suggestion service may use clusters of pre-approved messages to improve the quality of messages suggested to users. During a conversation, messages of the conversation may be processed with a neural network to compute a conversation encoding vector. The neural network may also be used to compute pre-approved message encoding vectors of the pre-approved messages. Distances between the conversation encoding vector and the pre-approved message encoding vectors may be used to select one or more clusters. Distances between the conversation encoding vector and the pre-approved message encoding vectors may then be used to select one or more pre-approved messages from the selected clusters. The selected pre-approved messages may then be presented as suggested messages to a user.

Abstract: A statistical language model may be used to simulate one or more users of a conversation. The statistical language model may be used to train a user to participate in a particular types of conversation by simulating communications by another type of user in the conversation. The communications may be simulated by selecting a simulation context from available simulation contexts and the simulation context may correspond to a difficulty level. Upon receiving a communication from a user, a responsive simulated communication may be generated by processing the received communication and the simulation context with the statistical language model. Upon completion of the simulation, another simulation context may be selected for the next simulation.

Abstract: In accordance with one aspect, methods and apparatus facilitate the filtering of unsolicited bulk electronic mail (email) sent from spammers. A plurality of recipient patterns for a plurality of emails from known spammers is logged. A plurality of recipient patterns for a plurality of emails from known non-spammers is also logged. A probabilistic model for predicting whether an unknown sender identity is a spammer is generated or modified based on the logged recipient patterns for the emails from known spammers and known non-spammers.

Abstract: A system and method for improved classification. A first classifier is trained using a first process running on at least one computing device using a first set of training images relating to a class of images. A set of additional images are selected using the first classifier from a source of additional images accessible to the computing device. The first set of training images and the set of additional images are merged using the computing device to create a second set of training images. A second classifier is trained using a second process running on the computing device using the second set of training images. A set of unclassified images are classified using the second classifier thereby creating a set of classified images. The first classifier and the second classifier employ different classification methods.

Abstract: A search engine determines a set of other images that are similar to a user-selected image, and presents those other images to the user. In determining whether two images are sufficiently similar to each other to merit presentation of one, the search engine determines a Euclidean distance between separate feature vectors that are associated with each of the images. Each such vector indicates diverse types of information that is known about the associated image. The types of information included within such a vector may include attributes that reflect visual characteristics that are visible in an image, verbal tags that have been associated with the image users in a community of users, concepts derived from those tags, coordinates that reflect a geographic location at which a camera that produced the image was when the camera produced the image, and concepts related to groups with which the image is associated.

Abstract: Methods and system for rendering context aware multimedia content include identifying a plurality of multimedia content that is uploaded for rendering. The uploaded multimedia content is examined to determine metadata associated with each of the plurality of multimedia contents. Contextual information associated with the metadata is identified and a grouping of the multimedia content into a plurality of groups is performed based on the contextual information. Each of the plurality of groups is then integrated into one or more photo stories. The photo stories are defined and rendered as content rich documents.

Abstract: Embodiments are directed towards using a community of weighted results from local and global message classifiers to determine whether a message is spam. Each local classifier may receive a message that is to be evaluated to determine whether it is spam. A local classifier receives the message and performs a classification of the message. The local classifier may receive predictions of whether the message is spam from at least one global classifier. The local and global predictions are combined using, in one embodiment, a regression analysis to generate a single local message classification. Combining the local and global predictions is directed towards enabling a community of predictions to be used to classify messages. The user may then re-classify this output, which in turn is used as feedback to modify weights to the local and received global predictions for a next message.

Abstract: Disclosed are methods and apparatus for improving images. At an image management system for storing a plurality of images from a plurality of users via a computer network, a new image is received and stored. So as to generate a new improved image, each patch of the new image is changed into an improved image patch based on selecting one or more selected mappings for converting one or more low-quality patches into one or more high-quality patches. The one or more selected mappings are determined from the images stored by the image management system. The new improved image is provided to the user.

Abstract: Disclosed are methods and apparatus for facilitating the filtering of unsolicited bulk electronic mail (email) sent from spammers. A plurality of recipient patterns for a plurality of emails from known spammers is logged. A plurality of recipient patterns for a plurality of emails from known non-spammers is also logged. A probabilistic model for predicting whether an unknown sender identity is a spammer is generated or modified based on the logged recipient patterns for the emails from known spammers and known non-spammers.

Abstract: A search engine determines a set of other images that are similar to a user-selected image, and presents those other images to the user. In determining whether two images are sufficiently similar to each other to merit presentation of one, the search engine determines a Euclidean distance between separate feature vectors that are associated with each of the images. Each such vector indicates diverse types of information that is known about the associated image. The types of information included within such a vector may include attributes that reflect visual characteristics that are visible in an image, verbal tags that have been associated with the image users in a community of users, concepts derived from those tags, coordinates that reflect a geographic location at which a camera that produced the image was when the camera produced the image, and concepts related to groups with which the image is associated.

Abstract: Methods and system for rendering context aware multimedia content include identifying a plurality of multimedia content that is uploaded for rendering. The uploaded multimedia content is examined to determine metadata associated with each of the plurality of multimedia contents. Contextual information associated with the metadata is identified and a grouping of the multimedia content into a plurality of groups is performed based on the contextual information. Each of the plurality of groups is then integrated into one or more photo stories. The photo stories are defined and rendered as content rich documents.

Abstract: Construct a statistical model for a plurality of multimedia objects identified in response to a search query, the statistical model comprising a plurality of probabilities, wherein each of the multimedia objects uniquely corresponding to a different one of a plurality of sets of feature values, each of the feature values of each of the sets of feature values being a characterization of the multimedia object corresponding to the set of feature values, and each of the probabilities being calculated for a different one of the multimedia objects based on the set of feature values corresponding to the multimedia object. Rank the multimedia objects based on their corresponding probabilities, such that a multimedia object having a relatively higher probability is ranked relatively higher.

Abstract: A system and method for improved classification. A first classifier is trained using a first process running on at least one computing device using a first set of training images relating to a class of images. A set of additional images are selected using the first classifier from a source of additional images accessible to the computing device. The first set of training images and the set of additional images are merged using the computing device to create a second set of training images. A second classifier is trained using a second process running on the computing device using the second set of training images. A set of unclassified images are classified using the second classifier thereby creating a set of classified images. The first classifier and the second classifier employ different classification methods.

Abstract: Embodiments are directed towards employing a playful incentive to encourage users to provide feedback that is useable to train a classifier. The classifier being associated with any of a variety of different settings, including but not limited to classifying: messages as ham/spam, images, advertising, bookmarking, music, videos, photographs, shopping, or the like. An animated image, such as a pet, provides an interface to the classifier that encourages and responds to user feedback. Users may share their classifiers or aspects thereof with other users to enable a community of knowledge to be applied to a classification task, while preserving privacy of the user feedback. One form of sharing may be within the context of a competitive game. Various evaluations may be performed on a classifier to indicate user feedback consistency, or quality. Classifiers may also be used to provide users with advertisements, products, or services based on the user's feedback.

Abstract: An improved system and method for disambiguating text strings labeling content objects is provided. A text string set may be received from a user. Frequencies of co-occurring text strings in a text collection may be obtained, and a disambiguation measure may be determined for a pair of text strings that each co-occur with a text string in the text string set. The disambiguation measure may be based on a weighted KL divergence of text string distributions that maximizes the value of divergence when a text string set may occur in different contexts. A disambiguation measure may be determined for a list of the top most common pairs of text strings that co-occur with the text string set, and the pairs of text strings may be output in decreasing order by disambiguation measure for those pairs of text strings with a disambiguation measure that exceeds a threshold.

Abstract: Embodiments are directed towards using a community of weighted results from local and global message classifiers to determine whether a message is spam. Each local classifier may receive a message that is to be evaluated to determine whether it is spam. A local classifier receives the message and performs a classification of the message. The local classifier may receive predictions of whether the message is spam from at least one global classifier. The local and global predictions are combined using, in one embodiment, a regression analysis to generate a single local message classification. Combining the local and global predictions is directed towards enabling a community of predictions to be used to classify messages. The user may then re-classify this output, which in turn is used as feedback to modify weights to the local and received global predictions for a next message.