Document retrieval method for searching topic type query in TED speech

Abstract

The invention relates to the technical field of information retrieval, and provides a semantic document retrieval method for searching topic type query in TED speech. The method comprises: training aneural network model by utilizing the existing query and document, and learning neural network model parameters; when a user inputs a query, a query likelihood retrieval model is used to obtain a preliminary retrieval result; and inputting the preliminary retrieval result into the neural network model with the fixed parameters for reordering, and determining a final retrieval result. According tothe method, the problem that a good effect cannot be achieved due to the fact that a traditional retrieval method in topic type query retrieval lacks semantic contact between queries and documents issolved; respectively modeling the topic type query and the speech document by introducing a neural network, and obtaining the semantic level correlation between the query and the document. In the neural network part, a recurrent neural network and a convolutional neural network are connected in series, and in addition, in order to solve the problem of gradient disappearance, a currently popular LSTM module is adopted.

Description

technical field [0001] The invention relates to the technical field of information retrieval, in particular to a document retrieval method for searching topic queries in TED speeches. Background technique [0002] TED (Technology Entertainment Design) is currently the most successful speech viewing platform. Searching is one of the main ways the platform makes speech available to users. Specifically, users can actively enter keywords in the search box or click on the keywords provided on the platform about topics, speakers, and subtitle languages ​​to search for speeches they are interested in. [0003] The retrieval method of the TED platform is based on the Boolean model. Other traditional retrieval models, such as Query Likelihood (QL), Sequence Dependency Model (SDM), BM25, etc., are all optimized on the basis of this model. BooleanModel (Cooper W S.Getting beyond Boole[J].Information Processing&Management,1988,24(3):243-248.) is the simplest and commonly used retrieva...

AI Technical Summary

Problems solved by technology

[0008] The key technical problem to be solved by the present invention is to solve the problem that the traditional retrieval method in the TED speech topic query retrieval cannot achieve better results due to the lack of semantic connection between the query and the document

Images