Classifying data objects

A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:

• obtaining data comprising a respective high-dimensional representation for each category label of a plurality of category labels that each correspond to a different category of a plurality of categories, wherein the high-dimensional representation of the category label is a numeric representation of the category label in a high-dimensional space;
• obtaining a new data object to be classified;
• processing the new data object using a deep neural network, wherein the deep neural network comprises a plurality of neural network layers and has been configured through training to:
• generate a plurality of initial classification scores for the new data object, wherein each initial classification score corresponds to a different category from the plurality of categories and represents a likelihood as determined by the deep neural network that the new data object belongs to the corresponding category;
• for each category of one or more of the plurality of categories, computing a respective product between i) the initial classification score for the category generated by the deep neural network and ii) the high-dimensional representation of the category label corresponding the category;
• summing the respective products of the one or more categories to generate an aggregate high-dimensional representation;
• identifying a first term in a vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation;
• and
• selecting the first term as a category label for the new data object.

A non-transitory computer storage medium encoded with a computer program, the computer program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

• obtaining data comprising a respective high-dimensional representation for each category label of a plurality of category labels that each correspond to a different category of a plurality of categories, wherein the high-dimensional representation of the category label is a numeric representation of the category label in a high-dimensional space;
• obtaining a new data object to be classified;
• processing the new data object using a deep neural network, wherein the deep neural network comprises a plurality of neural network layers and has been configured through training to:
• generate a plurality of initial classification scores for the new data object, wherein each initial classification score corresponds to a different category from the plurality of categories and represents a likelihood as determined by the deep neural network that the new data object belongs to the corresponding category;
• for each category of one or more of the plurality of categories, computing a respective product between i) the initial classification score for the category generated by the deep neural network and ii) the high-dimensional representation of the category label corresponding the category;
• summing the respective products of the one or more categories to generate an aggregate high-dimensional representation;
• identifying a first term in a vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation;
• and
• selecting the first term as a category label for the new data object.