Article retrieval model training method and device

Article retrieval model training method and device

The invention discloses an article retrieval model training method and device. According to one specific embodiment, the method comprises the steps that a training sample is generated in combination with a plurality of article description fragments and a query request in an original training sample,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WANG HUIMU, NIE GUANGTAO, TANG GUOYU, WANG BINBIN, LI MINGMING
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses an article retrieval model training method and device. According to one specific embodiment, the method comprises the steps that a training sample is generated in combination with a plurality of article description fragments and a query request in an original training sample, and the article description fragments are generated according to an article description text corresponding to the query request in the original training sample; and performing model training by taking the query request as input and the plurality of article description fragments as expected output to obtain an article retrieval model. According to the method, the text length and disorder degree of the article description text are reduced based on the article description fragment, the learning difficulty of the article retrieval model is reduced, and the accuracy of the article retrieval model is improved; according to the method, the retrieval task of the generative article retrieval model is redefined, so that the