基于句子轉(zhuǎn)換和雙注意力機制的歸納關(guān)系預測

打開文本圖片集

Inductive relation prediction based on sentence Transformer and dual attention mechanism

Li Weijun a，b? ，Liu Xueyang2，Liu Shixia，Wang Ziyia，Ding Jianpinga，Su Yileia （a.Colegeofuene&oKbafgs&asellgentossnofateEcs sion，North Minzu University，Yinchuan75oo21，China）

Abstract：Relation predictionisaimportant task in knowledgegraphcompletion，aimedat predicting mising relationships between entities.Existing inductiverelationprediction methodsoften facechalenges inadequatelymodeling semanticand structural information.Toaddress thisisse，thispaper proposedaninductiverelation predictionmodel basedonsentence transformationandadual-atentionmechanism.Theproposedmethodenhancedentitysemanticrepresentationsbyautomaticallyretrievingdescritionsandincorporatesadual-atentionmechanism，whichonsiderededgeandelationawarenes，toacu ratelymodelthecomplexinteractionsbetweeentities.Firstly，itextractedtheclosedsubgraphofthetargettripleanduseda random walk strategytosearchformuli-hoprelational paths.Thesetriplesand pathswerethen transformedinto natural language sentences，generating semanticall rich sentence embeddings.Next，it updated the subgraph embeddings using GCN andbidirectionalGRU，combiningsentenceandsubgraphembeddings tocapturebothstructuralandsemanticinformationExperimentalresultsonthree public datasets—WN18RR，F(xiàn)B15k-237，andNELL-995—demonstratethattheproposed method outperformsexisting methodsinbothtransformationandinductiverelationpredictiontasks，validatingtheimportanceof the dual-attention mechanismandsentence transformationin improving model performance.Thisapproach efectively enhances the accuracy and efficiency of relation prediction in knowledge graphs.

Key words：knowledge graph（KG）；inductiverelation prediction；sentence Transformer;dual atention mechanism；random walk pathfinding strategy

0 引言

知識圖譜（KG）是一種用于表示和存儲客觀世界知識的圖形化知識庫，通過三元組方式進行形式化描述，廣泛應用于網(wǎng)絡搜索[1]、社區(qū)檢測[2]和推薦系統(tǒng)[3]等任務。（剩余17867字）