Google Inc.

Noah B Coccaro

Nir Andelman

Adi Avidor

Mario Tanev

Ivan Davtchev

Ciprian Ioan Chelba

Patrick An Nguyen

Roshan Baliga

In one implementation, a computer-implemented method includes receiving, at a computer system, a request to predict a next word in a dialog being uttered by a speaker; accessing, by the computer system, a neural network comprising i) an input layer, ii) one or more hidden layers, and iii) an output layer; identifying the local context for the dialog of the speaker; selecting, by the computer system and using a semantic model, at least one vector that represents the semantic context for the dialog; applying input to the input layer of the neural network, the input comprising i) the local context of the dialog and ii) the values for the at least one vector; generating probability values for at least a portion of the candidate words; and providing, by the computer system and based on the probability values, information that identifies one or more of the candidate words.

Integration of semantic context information

Systems and methods of serving a content item to a user in a specific language are provided. An electronic document can be provided to a computing device over a network. A request to translate the electronic document from a first language to a second language can be received from the computing device. A language parameter for the computing device can be stored based on the request to translate the electronic document. A request for a content item to be provided to the computing device can be received. A content item can be selected from a content item database based on the stored language parameter and a geographic parameter indicating the content item is relevant to a geographic area local to the computing device. The content item can be provided to the computing device over the network.

Systems and methods of serving a content item to a user in a specific language

An audio shortcut may involve an audio command being used to represent a sequence of one or more inputs on a client device. When the client device receives the audio command, the client device may automatically perform the sequence of one or more inputs, as if this sequence were entered manually. If a threshold number of client devices share the same or a similar audio shortcut with a server device, the server device may make this audio shortcut available to additional client devices.

Crowd-sourced audio shortcuts

Methods, systems, and apparatus, including computer program products, in which input keystroke data can be interpreted using a current mapping and a determination can be made whether the current mapping is valid based upon the characters identified by the mapping and the keystroke data. Invalid mappings can be corrected by identifying a transliteration of the characters in an alternative language.

Automatic correction of user input based on dictionary

Methods, systems, and apparatus, including computer program products, in which input keystroke data can be interpreted by a current mapping and a determination can be made whether the current mapping is valid based upon the characters identified by the mapping and the keystroke data. Invalid mappings can be corrected based upon alternative mapping of the keystroke data.

Growing community of inventors

Mountain View, CA, United States of America

Noah B Coccaro