Method and device for excavating synonymous attribute words

Abstract

The invention provides a method and a device for excavating synonymous attribute words, wherein the method includes: based on an existing entity word dictionary and an existing attribute word dictionary, carrying out structured analysis on each query in a query set, extracting standard query which is formed by the combination of entity words and attribute words; aiming at each standard query, respectively calculating the click similarity between each non-standard query and the standard query, and confirming the non-standard query which has the same entity words as the current standard query, wherein the click similarity of the non-standard query meets the requirement of the preset similarity; removing the entity words identical to the current standard query in the confirmed non-standard query to obtain candidate synonymous attribute words; and scoring each synonymous attribute word, and based on the scores, confirming the synonymous attribute word of the attribute word in the current standard query. The manpower resource can be saved, and efficiency and a recall rate can be improved.

Description

【Technical field】 [0001] The invention relates to the field of computer technology, in particular to a method and device for mining synonymous attribute words. 【Background technique】 [0002] With the continuous development of network technology, search engines have become an important way for people to obtain information. By inputting a search term (query) in the search engine, users obtain search results returned by the search engine for the query. In order to return search results to users in a targeted manner, it is necessary to perform demand analysis on the query, in which entity attributes are the basis for analyzing user needs and also the basis for realizing structured search (vertical search). That is, the entity word and attribute word are analyzed from the query. For example, for the query "What is Andy Lau's height", the entity word is "Andy Lau" and the attribute word is "height". Know the specific information about Andy Lau's height. [0003] In the identifi...

AI Technical Summary

Problems solved by technology

[0003] In the identification process of entity attributes, entity words and attribute words are matched and identified through the preset entity word dictionary and attribute word dictionary respectively. However, usually the expression of entity words is relatively unique and fixed, while attribute words may have different expressions Usually, the attribute word dictionary contains a standardized expression form. For other synonymous attribute words, it is added manually or combined with thesaurus. The manual addition method consumes human resources, has low efficiency, and has a low recall rate. Low; combined with the thesaurus dictionary, there is also the problem of low recall rate. For example, for some colloquial expressions such as "how tall" and "head" that are not in the thesaurus dictionary, they cannot be recalled

Images