Please enable JavaScript.

Coggle requires JavaScript to display documents.

Knowledge Graph Completion (Entity and Relation Embedding (Learning Entity…

- - - - Maosong Sun
      - YanKan Lin
    - - TransR
        
        learn embeddings by first projecting entities from entity space to corresponding relation space
        
        build translations between projected entities
        
        Evaluation
        
        Link Prediction
        
        Triple Classification
        
        Relational Fact Exaction
        
        Code
        
        //github.com/mrlyk423/relation extraction
        
        Data Sets and Experiment Setting
        
        Link Prediction
        
        Triple Classification
        
        model entities and relations in distinct spaces, i.e., entity space and multiple relation spaces (i.e., relation-specific entity spaces), and performs the translation in the corresponding relation space
        :star:
        
        cluster-based TransR (CTransR)
        
        clustering diverse head-tail entity pairs into groups
        
        learning distinct relation vectors for each group
        
        STEP
        
        segment input instances into several groups
        
        for a specific relation r, all entity pairs (h, t) in the training data are clustered into multiple groups, and entity pairs in each group are expected to exhibit similar r relation
        
        All entity pairs (h, t) are represented with their vector offsets (h−t) for clustering, where h and t are obtained with TransE
        
        we learn a separate relation vector rc for each cluster and matrix Mr for each relation, respectively.
        
        define the projected vectors of entities as hr,c = hMr and tr,c = tMr
      - TransH
        
        Wang, Z.; Zhang, J.; Feng, J.; and Chen, Z. 2014. Knowl- edge graph embedding by translating on hyperplanes. In Proceedings ofAAAI, 1112–1119
      - TransE
        
        Mikolov, T.; Sutskever, I.; Chen, K.; Corrado, G. S.; and Dean, J. 2013b. Distributed representations of words and phrases and their compositionality. In Proceedings ofNIPS, 3111–3119
        
        learns vector embeddings for both entities and relationships
        
        Bordes, A.; Usunier, N.; Garcia-Duran, A.; Weston, J.; and Yakhnenko, O. 2013. Translating embeddings for modeling multi-relational data. In Proceedings of NIPS, 2787–2795.