AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
NeuInfer is capable of dealing with the newly proposed flexible knowledge inference, which tackles the inference on partial facts consisting of a primary triple coupled with any number of its auxiliary descriptive attributevalue pair(s)

NeuInfer: Knowledge Inference on N-ary Facts

ACL, pp.6141-6151, (2020)

被引用1|浏览198
EI
下载 PDF 全文
引用
微博一下

摘要

Knowledge inference on knowledge graph has attracted extensive attention, which aims to find out connotative valid facts in knowledge graph and is very helpful for improving the performance of many downstream applications. However, researchers have mainly poured attention to knowledge inference on binary facts. The studies on n-ary facts ...更多

代码

数据

0
简介
  • With the introduction of connotative valid facts, knowledge inference on knowledge graph improves the performance of many downstream applications, such as vertical search and question answering (Dong et al, 2015; Lukovnikov et al, 2017).
  • Existing studies (Nickel et al, 2016; Wang et al, 2017) mainly focus on knowledge inference on binary facts with two entities connected with a certain binary relation, represented as triples,.
  • They attempt to infer the unknown head/tail entity or the unknown relation of a given binary fact.
重点内容
  • With the introduction of connotative valid facts, knowledge inference on knowledge graph improves the performance of many downstream applications, such as vertical search and question answering (Dong et al, 2015; Lukovnikov et al, 2017)
  • Existing studies (Nickel et al, 2016; Wang et al, 2017) mainly focus on knowledge inference on binary facts with two entities connected with a certain binary relation, represented as triples
  • Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6141–6151 July 5 - 10, 2020. c 2020 Association for Computational Linguistics refer the former as simple knowledge inference, while the latter as flexible knowledge inference. With these considerations in mind, in this paper, by discriminating the information in the same n-ary fact, we propose a neural network model, called NeuInfer, to conduct both simple and flexible knowledge inference on n-ary facts
  • We treat the information in the same n-ary fact discriminatingly and represent each n-ary fact as a primary triple coupled with a set of its auxiliary descriptive attribute-value pair(s)
  • NeuInfer is capable of dealing with the newly proposed flexible knowledge inference, which tackles the inference on partial facts consisting of a primary triple coupled with any number of its auxiliary descriptive attributevalue pair(s)
方法
  • 5.3.1 Baselines Knowledge inference methods on n-ary facts are scarce.
  • The representative methods are mTransH (Wen et al, 2016) and its modified version RAE (Zhang et al, 2018), and the state-of-the-art one is NaLP (Guan et al, 2019).
  • As m-TransH is worse than RAE, following NaLP, the authors do not adopt it as a baseline.
  • It is ascribed to the reasonable modeling of n-ary facts, which improves the performance of simple entity inference and is beneficial to pick the exact right relations/attributes out.
结论
  • NeuInfer is capable of dealing with the newly proposed flexible knowledge inference, which tackles the inference on partial facts consisting of a primary triple coupled with any number of its auxiliary descriptive attributevalue pair(s).
  • On simple entity inference, NeuInfer outperforms the state-of-the-art method significantly in terms of all the metrics.
  • NeuInfer improves the performance of Hits@3 even by 16.2% on JF17K.
  • The authors use only n-ary facts in the datasets to conduct knowledge inference.
  • To further improve the method, the authors will explore the introduction of additional information, such as rules and external texts
表格
  • Table1: The statistics of the datasets
  • Table2: Experimental results of simple entity inference
  • Table3: Experimental results of simple relation inference
  • Table4: Experimental results of flexible knowledge inference
  • Table5: Experimental results of simple entity inference on binary and n-ary categories of JF17K and WikiPeople
  • Table6: Detailed experimental results on inferring head/tail entities
  • Table7: Experimental results on inferring attribute values
Download tables as Excel
相关工作
  • 2.1 Knowledge Inference on Binary Facts

    They can be divided into tensor/matrix based methods, translation based methods, and neural network based ones.

    The quintessential one of tensor/matrix based methods is RESCAL (Nickel et al, 2011). It relates a knowledge graph to a three-way tensor of head entities, relations, and tail entities. The learned embeddings of entities and relations via minimizing the reconstruction error of the tensor are used to reconstruct the tensor. And binary facts corresponding to entries of large values are treated as valid. Similarly, ComplEx (Trouillon et al, 2016) relates each relation to a matrix of head and tail entities, which is decomposed and learned like RESCAL. To improve the embeddings and thus the performance of inference, researchers further introduce the constraints of entities and relations (Ding et al, 2018; Jain et al, 2018).
基金
  • The work is supported by the National Key Research and Development Program of China under grant 2016YFB1000902, the National Natural Science Foundation of China under grants U1911401, 61772501, U1836206, 91646120, and 61722211, the GFKJ Innovation Program, Beijing Academy of Artificial Intelligence (BAAI) under grant BAAI2019ZD0306, and the Lenovo-CAS Joint Lab Youth Scientist Project
引用论文
  • Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. 2008. Freebase: A collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, pages 1247–1250.
    Google ScholarLocate open access versionFindings
  • Antoine Bordes, Nicolas Usunier, Alberto GarciaDuran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multirelational data. In Proceedings of the 26th International Conference on Neural Information Processing Systems, pages 2787–2795.
    Google ScholarLocate open access versionFindings
  • Mingyang Chen, Wen Zhang, Wei Zhang, Qiang Chen, and Huajun Chen. 2019. Meta relational learning for few-shot link prediction in knowledge graphs. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 4208–4217, Hong Kong, China.
    Google ScholarLocate open access versionFindings
  • Tim Dettmers, Pasquale Minervini, Pontus Stenetorp, and Sebastian Riedel. 2018. Convolutional 2D knowledge graph embeddings. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pages 1811–1818.
    Google ScholarLocate open access versionFindings
  • Boyang Ding, Quan Wang, Bin Wang, and Li Guo. 2018. Improving knowledge graph embedding using simple constraints. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 110–121.
    Google ScholarLocate open access versionFindings
  • Li Dong, Furu Wei, Ming Zhou, and Ke Xu. 2015. Question answering over Freebase with multicolumn convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pages 260–269.
    Google ScholarLocate open access versionFindings
  • Takuma Ebisu and Ryutaro Ichise. 2018. TorusE: Knowledge graph embedding on a Lie group. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, pages 1819–1826.
    Google ScholarLocate open access versionFindings
  • Saiping Guan, Xiaolong Jin, Yuanzhuo Wang, and Xueqi Cheng. 201Shared embedding based neural networks for knowledge graph completion. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 247–256.
    Google ScholarLocate open access versionFindings
  • Saiping Guan, Xiaolong Jin, Yuanzhuo Wang, and Xueqi Cheng. 201Link prediction on n-ary relational data. In Proceedings of the 28th International Conference on World Wide Web, pages 583–593.
    Google ScholarLocate open access versionFindings
  • Shu Guo, Quan Wang, Bin Wang, Lihong Wang, and Li Guo. 2015. Semantically smooth knowledge graph embedding. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pages 84–94.
    Google ScholarLocate open access versionFindings
  • Prachi Jain, Pankaj Kumar, Soumen Chakrabarti, et al. 2018. Type-sensitive knowledge base inference without explicit type supervision. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 75–80.
    Google ScholarLocate open access versionFindings
  • Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Knowledge graph embedding via dynamic mapping matrix. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pages 687–696.
    Google ScholarLocate open access versionFindings
  • Yantao Jia, Yuanzhuo Wang, Hailun Lin, Xiaolong Jin, and Xueqi Cheng. 2016. Locally adaptive translation for knowledge graph embedding. In Proceedings of the 30th AAAI Conference on Artificial Intelligence, pages 992–998.
    Google ScholarLocate open access versionFindings
  • Xiaotian Jiang, Quan Wang, and Bin Wang. 2019. Adaptive convolution for multi-relational learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 978–987, Minneapolis, Minnesota.
    Google ScholarLocate open access versionFindings
  • Diederik Kingma and Jimmy Ba. 20Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations.
    Google ScholarLocate open access versionFindings
  • Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, and Song Liu. 2015a. Modeling relation paths for representation learning of knowledge bases. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 705–714.
    Google ScholarLocate open access versionFindings
  • Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. 2015b. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the 29th AAAI Conference on Artificial Intelligence, pages 2181–2187.
    Google ScholarLocate open access versionFindings
  • Denis Lukovnikov, Asja Fischer, Jens Lehmann, and Soren Auer. 2017. Neural network-based question answering over knowledge graphs on word and character level. In Proceedings of the 26th International Conference on World Wide Web, pages 1211–1220.
    Google ScholarLocate open access versionFindings
  • Deepak Nathani, Jatin Chauhan, Charu Sharma, and Manohar Kaul. 20Learning attention-based embeddings for relation prediction in knowledge graphs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4710–4723, Florence, Italy.
    Google ScholarLocate open access versionFindings
  • Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, and Dinh Phung. 2018. A novel embedding model for knowledge base completion based on convolutional neural network. In Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 327–333.
    Google ScholarLocate open access versionFindings
  • Maximilian Nickel, Kevin Murphy, Volker Tresp, and Evgeniy Gabrilovich. 2016. A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 104(1):11–33.
    Google ScholarLocate open access versionFindings
  • Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A three-way model for collective learning on multi-relational data. In Proceedings of the 28th International Conference on Machine Learning, pages 809–816.
    Google ScholarLocate open access versionFindings
  • Fabian M Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. Yago: A core of semantic knowledge. In Proceedings of the 16th International Conference on World Wide Web, pages 697–706.
    Google ScholarLocate open access versionFindings
  • Yi Tay, Anh Tuan Luu, and Siu Cheung Hui. 2017. Non-parametric estimation of multiple embeddings for link prediction on dynamic knowledge graphs. In Proceedings of the 31st AAAI Conference on Artificial Intelligence, pages 1243–1249.
    Google ScholarLocate open access versionFindings
  • Theo Trouillon, Johannes Welbl, Sebastian Riedel, Eric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In Proceedings of the 33rd International Conference on Machine Learning, pages 2071–2080.
    Google ScholarLocate open access versionFindings
  • Denny Vrandecicand Markus Krotzsch. 2014. Wikidata: A free collaborative knowledgebase. Communications of the ACM, 57(10):78–85.
    Google ScholarLocate open access versionFindings
  • Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering, 29(12):2724– 2743.
    Google ScholarLocate open access versionFindings
  • Zhen Wang, Jianwen Zhang, Jianlin Feng, and Zheng Chen. 2014. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the 28th AAAI Conference on Artificial Intelligence, pages 1112–1119.
    Google ScholarLocate open access versionFindings
  • Jianfeng Wen, Jianxin Li, Yongyi Mao, Shini Chen, and Richong Zhang. 2016. On the representation and embedding of knowledge bases beyond binary relations. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, pages 1300–1307.
    Google ScholarLocate open access versionFindings
  • Han Xiao, Minlie Huang, and Xiaoyan Zhu. 2016. TransG: A generative model for knowledge graph embedding. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 2316–2325.
    Google ScholarLocate open access versionFindings
  • Richong Zhang, Junpeng Li, Jiajie Mei, and Yongyi Mao. 2018. Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding. In Proceedings of the 27th International Conference on World Wide Web, pages 1185–1194.
    Google ScholarLocate open access versionFindings
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科