Topics in relevance ranking model for web search

摘要

Described is a technology by which topics corresponding to web pages are used in relevance ranking of those pages. Topics are extracted from each web page of a set of web pages that are found via a query. For example, text such as nouns may be extracted from the title, anchor texts and URL of a page, and used as the topics. The extracted topics from a page are used to compute a relevance score for that page based on an evaluation of that page's topics against the query. The pages are then ranked relative to one another based at least in part on the relevance score computed for each page, such as by determining a matching level for each page, ranking pages by each level, and ranking pages within each level. Also described is training a model to perform the relevance scoring and/or ranking.

主权项

1. A method performed on a computing device, the method comprising:
computing, by the computing device, a relevance score for each topic of a plurality of topics extracted from each page of a plurality of pages that correspond to a query, where the each topic represents a subject of the each page, where each relevance score is based on a degree of matching between an encoded version of the query and an encoded version of the corresponding each extracted topic; calculating, for the each page based on the corresponding computed relevance scores, a probability for each of a plurality of matching levels; selecting, for the each page, a matching level that has the highest calculated probability of each of the plurality of matching levels; and ranking the plurality of pages according to their selected matching levels and, within each same selected matching level, according to their calculated probabilities.