知识表示学习研究进展.pdfVIP

计算机研究与发展 DOI: 10. 7544fissn1000-1239. 2016. Journal of Computer Research and Development 53(2): 247-261 , 2016 知识表示学习研究进展 刘知远孙茂松林衍凯谢若冻 (清华大学计算机科学与技术系 北京 100084) (智能技术与系统国家重点实验室(清华大学) 北京 100084) (清华信息科学与技术国家实验室(筹〉 北京 100084) Cliuzy@tsinghua. edu. cn) Knowledge Representation Learning: A Review Liu Zhiyuan , Sun Maosong , Lin Yankai , and Xie Ruobing (Deρartment of Comρuter Science and Technology , Tsinghua University , Beijing 100084) (State Key Laboratory of Intelligent Technology and Systems (Tsinghua University) , Beijing 100084) (Tsinghua National Laboratory for Information Science and Technology , Beijing 100084) Abstract Knowledge bases are usually represented as networks with entities as nodes and relations as edges. With network representation of knowledge bases , specific algorithms have to be designed to store and utilize knowledge bases , which are usually time consuming and suffer from data sparsity issue. Recently , representation learning , delegated by deep learning , has attracted many attentions in natural language processing , computer VlS lOn and speech analysis. Representation learning aims to project the interested objects into a dense , real-valued and low-dimensional semantic space , whereas knowledge representation learning focuses on representation learning of entities and relations in knowledge bases. Representation learning can efficiently measure semantic correlations of entities and relations , alleviate sparsity issues , and significantly improve the performance of knòwledge acquisition , fusion and inference. ln this paper , we wiU introduce the recent advances of representation learning , summarize the key challenges and possible solutions , and