Scoring Concept Terms Using a Deep Network

摘要

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes 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.

主权项

1. A system comprising:
a deep network implemented in one or more computers that defines a plurality of layers of non-linear operations, wherein the deep network comprises:
an embedding function layer configured to:
receive an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource, andprocess each of the features using a respective embedding function to generate one or more numeric values, andone or more neural network layers configured to:
receive the floating point values, andprocess the floating point 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 a classifier configured to:
process 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.