Clickthrough-based latent semantic model

摘要

There is provided a computer-implemented method and system for ranking documents. The method includes identifying a number of query-document pairs based on clickthrough data for a number of documents. The method also includes building a latent semantic model based on the query-document pairs and ranking the documents for a search based on the latent semantic model.

主权项

1. A computer-implemented method for ranking documents, comprising:
identifying a plurality of query-document pairs based on clickthrough data for a plurality of documents; building a latent semantic model based on the plurality of query-document pairs, wherein the plurality of query-document pairs comprises a plurality of query-title pairs, wherein the title in each query-title pair is a title of one of the documents of the plurality of documents, and wherein building the latent semantic model comprises building a bilingual topic model, a query being considered as expressed in a first language and the document being considered as expressed in a second language, by using the plurality of query-title pairs to learn a semantic representation of a query based on a likelihood that the query is a semantics-based translation of each of the plurality of documents; ranking the plurality of documents for a Web search based on a distance between vector representations of a query and a title of each of the plurality of documents within a semantic space, wherein a projection matrix is used to map the vector representations of the query and the title of each of the plurality of documents to the semantic space, wherein the semantic space comprises a dense, low-dimensional space; and ranking the plurality of documents for the Web search based on the latent semantic model.