Google Inc.

Kaisuke Nakajima

Jennifer W Lin

Pedro Jose Moreno Mengibar

Brian Strope

Fadi Biadsy

Daniel Martin Bikel

A method, computer program product, and computing system for providing a plurality of users of a social network with the ability to indicate affinity with an electronic object. An indication is received from a first user of the plurality of users to initiate an object-specific, synchronous communication session concerning the electronic object. Electronic invitations to join the object-specific, synchronous communication session are provided to one or more invited users of the plurality of users of the social network. A request is received, from at least one of the invited users, to join the object-specific, synchronous communication session. The object-specific, synchronous communication session is provided for the first user and the at least one of the invited users.

Synchronous communication system and method

Various aspects of the subject technology relate to systems, methods, and machine-readable media for prioritizing content (e.g., a post on a social networking site) based on a prioritized list of recipients. According to some aspects, a system receives a post associated with a prioritized list of recipients, wherein the prioritized list of recipients comprises an assignment, made by a publisher of the post, of a recipient user to a priority category, prioritizes the post based on the priority category assigned to the recipient user, and provides for display of the post in a user interface associated with the recipient user based on the score for the post.

Ranking posts based on a prioritized list of recipients

In one example, a method includes receiving, by a first computing device and from a second computing device, an image comprising an object. A user may be associated with a social networking service and the second computing device. The method further includes selecting a social group associated with the user in the social networking service. The selection may be based at least in part on one or more characteristics associated with the object. The method also includes sending, by the first computing device to the second computing device, an indication of the social group selected by the first computing device.

Social group suggestions within a social network

A set of benchmark text strings may be classified to provide a set of benchmark classifications. The benchmark text strings in the set may correspond to a benchmark corpus of benchmark utterances in a particular language. A benchmark classification distribution of the set of benchmark classifications may be determined. A respective classification for each text string in a corpus of text strings may also be determined. Text strings from the corpus of text strings may be sampled to form a training corpus of training text strings such that the classifications of the training text strings have a training text string classification distribution that is based on the benchmark classification distribution. The training corpus of training text strings may be used to train an automatic speech recognition (ASR) system.

Sampling training data for an automatic speech recognition system based on a benchmark classification distribution

Systems and methods for using a digital image in a social networking system may use digital image to identify a physical entity. Information about the identified physical entity may be provided to an electronic display for review by a user. The user may perform a social networking action with the identified physical entity or a website associated with the physical entity. Social networking actions may include rating or commenting about the physical entity or the associated website via a social networking system. Social networking actions may also include sharing information about the physical entity or associated website with another user via the social networking system.

Using a digital image in a social networking system

Aspects of the present disclosure provide techniques that may enable social annotation data to be displayed based on an ordered arrangement. In one example, a method includes receiving an indication of a selection of a social annotation field displayed at a graphical user interface (GUI), and updating the GUI to include social information associated with a portion of the plurality of other users and a plurality of graphical indications selectable by the user to change an order of the social information, wherein the social information is based on the social annotation data and is output in an ordered arrangement associated with a graphical indication displayed at the GUI. The method may also include receiving an indication of a selection of another graphical indication, and updating, based on the selection, the GUI to include the social information associated with another portion of the plurality of other users in another ordered arrangement.

Displaying social annotation data

A computer-implemented method is provided, according to which, an indication of a plurality of attributes of user interaction with one or more electronic messages in a user account is received, a rank value for each of the one or more electronic messages based on the plurality of attributes of user interaction with the one or more electronic messages is determined, the one or more electronic messages in the user account based on the determined rank value are sorted, and the sorted one or more electronic messages are provided for display in accordance with the determined rank value.

User productivity by showing most viewed messages

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for initializing language models for automatic speech recognition. In one aspect, a method includes receiving logged speech recognition results from an existing corpus that is specific to a given language and a target context, generating a target corpus by machine-translating the logged speech recognition results from the given language to a different, target language, and estimating a language model that is specific to the different, target language and the same, target context, using the target corpus.

Growing community of inventors

San Jose, CA, United States of America

Kaisuke Nakajima