Author:
,Mahure Swapnil S.,Khobragade Anish R.,
Abstract
Knowledge graphs are an important evolving field in Artificial Intelligence domain which has multiple applications such as in question answering, important information retrieval, information recommendation, Natural language processing etc. Knowledge graph has one big limitation i.e. Incompleteness, it is due to because of real world data are dynamic and continues evolving. This incompleteness of Knowledge graph can be overcome or minimized by using representation learning models. There are several models which are classified on the base of translation distance, semantic information and NN (Neural Network) based. Earlier the various embedding models are test on mostly two well-known datasets WN18RR & FB15k-237. In this paper, new dataset i.e. ArtGraph has been utilised for link prediction using representation learning models to enhance the utilization of ArtGraph in various domains. Experimental results shown ConvKB performed better over the other models for link prediction task.
Publisher
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Reference18 articles.
1. Nguyen, Dai Quoc, et al. "A novel embedding model for knowledge base completion based on convolutional neural network." arXiv preprint arXiv:1712.02121 (2017). https://doi.org/10.18653/v1/N18-2053
2. Dettmers, Tim, et al. "Convolutional 2d knowledge graph embeddings." Proceedings of the AAAI conference on artificial intelligence. Vol. 32. No. 1. 2018. https://doi.org/10.1609/aaai.v32i1.11573
3. Castellano, Giovanna, Giovanni Sansaro, and Gennaro Vessio. "Integrating contextual knowledge to visual features for fine art classification." arXiv preprint arXiv:2105.15028 (2021).
4. Wang, Meihong, Linling Qiu, and Xiaoli Wang. "A survey on knowledge graph embeddings for link prediction." Symmetry 13.3 (2021): 485. https://doi.org/10.3390/sym13030485
5. Bordes, Antoine, et al. "Translating embeddings for modeling multi-relational data." Advances in neural information processing systems 26 (2013).