A Query Expansion Method for Conversational Entity Search

Abstract

The invention discloses a conversational entity search-oriented query expansion method. The method comprises the steps of preprocessing a Wikipedia document set to obtain a data set D; traversing eachdocument d in the data set D to obtain a keyword reverse index Ik, an entity reverse index Ie and entity class mapping IE; extracting semantic information in WordNet and entity related information inYAGO3; according to a historical query result, constructing a historical result cache queue L; according to a current query Q of a user, retrieving Ik, Ie and IE to obtain pseudo-relevance feedback QPRF, and analyzing the historical result in L by utilizing the semantic information and the entity related information to obtain historical feedback Qh; based on the current query Q, the pseudo-relevance feedback QPRF and the historical feedback Qh, generating an extended query QE, and re-retrieving and sorting Ik, Ie and IE by utilizing QE to obtain a final result set R; and updating the cache queue L by utilizing R. The query process is shortened while the query overhead is reduced.

Description

technical field [0001] The present invention relates to the field of entity search, and more specifically, relates to a query expansion method for conversational entity search. Background technique [0002] Conversational entity search is to quickly and accurately retrieve subject-related entity objects (such as people, organizations, locations, etc.) and corresponding attributes in Web data through multiple rounds of user-interactive query. Compared with traditional entity search, conversational entity search decomposes user intent into a series of queries. In each round of query, users will propose new queries or modify original queries based on the results of historical queries. In this case, the information described by a single round of query is generally incomplete. At the same time, the continuous evolution of the query may also cause the content of the conversation to deviate from the target topic. Consistency is a key problem to be solved by conversational entity s...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the problem that none of the existing query expansion methods take into account the effect of historical factors and are mainly aimed at one-time queries rather than conversational queries, so they cannot fully understand user intentions and generate single Round query drift, which in turn affects the user's subsequent query and prolongs the query process. At the same time, the consistency of the topic of the conversation cannot be guaranteed, which reduces the efficiency of the conversational entity search.

Images