| 摘要 |
A deep structured semantic module (DSSM) is described herein which uses a model that is discriminatively trained based on click-through data, e.g., such that a conditional likelihood of clicked documents, given respective queries, is maximized, and a condition likelihood of non-clicked documents, given the queries, is reduced. In operation, after training is complete, the DSSM maps an input item into an output item expressed in a semantic space, using the trained model. To facilitate training and runtime operation, a dimensionality-reduction module (DRM) can reduce the dimensionality of the input item that is fed to the DSSM. A search engine may use the above-summarized functionality to convert a query and a plurality of documents into the common semantic space, and then determine the similarity between the query and documents in the semantic space. The search engine may then rank the documents based, at least in part, on the similarity measures. |
| 主权项 |
1. One or more computing devices that implement a projection module, comprising:
a dimensionality-reduction module configured to:
receive an input item that represents linguistic information; andtransform the input item into a lower-dimension item,the input item being expressed in a first space having a first dimensionality,the lower-dimension item being expressed in a second space having a second dimensionality, andthe second dimensionality being smaller than the first dimensionality; and a deep structured semantic module configured to:
receive the lower-dimension item from the dimensionality-reduction module; andproject, using a model, the lower-dimension item into an output item,the output item being expressed in a semantic space, andthe model being discriminatively trained based on click-through data. |
