Method and apparatus for automatically identifying compounds

摘要

One embodiment of the present invention provides a system that automatically identifies compounds, such as bigrams or n-grams. During operation, the system obtains selections of search results which were selected by one or more users, wherein the search results were previously generated by a search engine in response to queries containing search terms. Next, the system forms a set of candidate compounds from the queries, wherein each candidate compound comprises n consecutive terms from a query. Then, for each candidate compound in the set, the system analyzes the selections of search results to calculate a likelihood that the candidate compound is a compound.

主权项

1. A computer-implemented method comprising:
identifying a candidate n-gram that includes two or more consecutive terms of a search query; determining a first quantity of search results that (i) were identified as responsive to the search query, and (ii) have been selected by other users; determining a second quantity of the search results that (i) were identified as responsive to the search query, (ii) have been selected by the other users, and (iii) are associated with text in which the candidate n-gram occurs; determining a value using the first quantity and the second quantity; and classifying the candidate n-gram as a particular type of n-gram, from among multiple types of n-grams, based on the determined value.