Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a textual term; determining, by one or more computers, a vector representing a phonetic feature of the textual term; comparing the vector representing the phonetic feature of the textual term with a reference vector representing a phonetic feature of a reference textual term; and classifying the textual term based on the comparing the vector with the reference vector.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing computational graphs on distributed computing devices.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining a textual term; determining, by one or more computers, a vector representing a phonetic feature of the textual term; comparing the vector representing the phonetic feature of the textual term with a reference vector representing a phonetic feature of a reference textual term; and classifying the textual term based on the comparing the vector with the reference vector.

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating compressed representations from a co-occurrence matrix. A method includes obtaining a set of sub matrices of a co-occurrence matrix, where each row of the co-occurrence matrix corresponds to a feature from a first feature vocabulary and each column of the co-occurrence matrix corresponds to a feature from a second feature vocabulary; selecting a sub matrix, wherein the sub matrix is associated with a particular row block and column block of the co-occurrence matrix; assigning respective d-dimensional initial row and column embedding vectors to each row and column from the particular row and column blocks, respectively; and determining a final row embedding vector and a final column embedding vector by iteratively adjusting the initial row embedding vectors and the initial column embedding vectors using the co-occurrence matrix.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for disambiguating word sense. One of the methods includes maintaining a respective word sense numeric representation of each of a plurality of word senses of a particular word; receiving a request to determine the word sense of the particular word when included in a particular text sequence, the particular text sequence comprising one or more context words and the particular word; determining a context numeric representation of the context words in the particular text sequence; and selecting a word sense of the plurality of word senses having a word sense numeric representation that is closest to the context numeric representation as the word sense of the particular word when included in the particular text sequence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a request for information about a term from a user; obtaining, at one or more processors, one or more characteristics of the user; obtaining, at the one or more processors, a template including a plurality of attributes associated with the term; generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the plurality of attributes in the template; and providing for output, data representing the response.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a request for information about a term from a user; obtaining, at one or more processors, one or more characteristics of the user; obtaining, at the one or more processors, a template including a plurality of attributes associated with the term; generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the plurality of attributes in the template; and providing for output, data representing the response.

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating compressed representations from a co-occurrence matrix. A method includes obtaining a set of sub matrices of a co-occurrence matrix, where each row of the co-occurrence matrix corresponds to a feature from a first feature vocabulary and each column of the co-occurrence matrix corresponds to a feature from a second feature vocabulary; selecting a sub matrix, wherein the sub matrix is associated with a particular row block and column block of the co-occurrence matrix; assigning respective d-dimensional initial row and column embedding vectors to each row and column from the particular row and column blocks, respectively; and determining a final row embedding vector and a final column embedding vector by iteratively adjusting the initial row embedding vectors and the initial column embedding vectors using the co-occurrence matrix.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a request for information about a term from a user; obtaining, at one or more processors, one or more characteristics of the user; obtaining, at the one or more processors, a template including a plurality of attributes associated with the term; generating, at the one or more processors and based on the one or more characteristics of the user, a response, the response including a respective description for each attribute of the plurality of attributes in the template; and providing for output, data representing the response.

Abstract: A device may receive, from a peripheral device, information for controlling the peripheral device. The information for controlling the peripheral device may include information identifying a voice command associated with the peripheral device and information identifying a function corresponding to the voice command. The device may receive, from a user, the voice command. The device may cause the peripheral device to perform the function based on receiving the voice command.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying voice inputs. The methods, systems, and apparatus include actions of providing an answer to a first voice input from a user and receiving visual or audio data corresponding to a second voice input. Further actions include classifying the second voice input as a follow on request to the first voice input or as deliberation on the answer, based on the visual data or the audio data. Additionally, the actions include determining whether to provide a response to the second voice input based on the classification of the second voice input.

Abstract: A device may receive an image of a user. The device may compare the image to an image of a known user and an image of an unknown user. The device may select, based comparing the image to the image of a known user and the image of an unknown user, one of: the image of the known user, or the image of the unknown user. The device may identify, when the image of the known user is selected, the user as the known user. The device may not identify the user when the image of the unknown user is selected.

Abstract: A device may receive, from a peripheral device, information for controlling the peripheral device. The information for controlling the peripheral device may include information identifying a voice command associated with the peripheral device and information identifying a function corresponding to the voice command. The device may receive, from a user, the voice command. The device may cause the peripheral device to perform the function based on receiving the voice command.