Scoring Concept Terms Using a Deep Network

A method for training a system for predicting a relevance of each of a set of pre-determined concept terms to resources, wherein the system includes an embedding function layer, one or more neural network layers, and a classifier, and wherein the method comprises:

• obtaining data identifying training resources and one or more respective associated concept terms for each of the training resources;
• specifying output criteria for a respective predicted output generated by the classifier for each of the training resources;
• and
• training the embedding function layer, the neural network layers, and the classifier based on respective features of each the training resources and on the specified output criteria, wherein each feature is a value of a respective attribute of the resource.

A method performed by one or more computers, the method comprising:

• receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource;
• processing each of the features using a respective embedding function to generate one or more numeric values;
• processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values;
• and
• processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.

A system comprising one or more computers and one or more storage devices storing instruction and wherein the method comprises:

• obtaining data identifying training resources and one or more respective associated concept terms for each of the training resources;
• specifying output criteria for a respective predicted output generated by the classifier for each of the training resources;
• and
• training a concept term scoring system for predicting a relevance of each of a set of pre-determined concept terms to resources, wherein the concept term scoring system includes an embedding function layer, one or more neural network layers, and a classifier, and wherein training the concept term scoring system comprises training the embedding function layer, the neural network layers, and the classifier based on respective features of each the training resources and on the specified output criteria, wherein each feature is a value of a respective attribute of the resource.

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

• receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource;
• processing each of the features using a respective embedding function to generate one or more numeric values;
• processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values;
• and
• processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource.

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

• obtaining data identifying training resources and one or more respective associated concept terms for each of the training resources;
• specifying output criteria for a respective predicted output generated by the classifier for each of the training resources;
• and
• training a concept term scoring system for predicting a relevance of each of a set of pre-determined concept terms to resources, wherein the concept term scoring system includes an embedding function layer, one or more neural network layers, and a classifier, and wherein training the concept term scoring system comprises training the embedding function layer, the neural network layers, and the classifier based on respective features of each the training resources and on the specified output criteria, wherein each feature is a value of a respective attribute of the resource.