-
摘要: 圍繞知識圖譜的全生命周期技術，從知識抽取、知識融合、知識推理、知識應用幾個層面展開綜述，重點介紹了知識融合技術和知識推理技術。通過知識抽取技術，可從已有的結構化、半結構化、非結構化樣本源以及一些開源的百科類網站抽取實體、關系、屬性等知識要素。通過知識融合，可消除實體、關系、屬性等指稱項與實體對象之間的歧義，得到一系列基本的事實表達。通過本體抽取、知識推理和質量評估形成最終的知識圖譜庫。按照知識抽取、知識融合、知識推理3個步驟對知識圖譜迭代更新，實現碎片化的互聯網知識的自動抽取、自動關聯和融合、自動加工，從而擁有詞條自動化鏈接、詞條編輯輔助功能，最終達成全流程自動化知識獲取的目標。最后，討論知識圖譜未來的發展方向與可能存在的挑戰。Abstract: The Google knowledge graph is a knowledge base used by Google and its services to enhance the search engine's results with information gathered from a variety of sources. Since its inception by Google to improve users' quality of experience of the search engine, the knowledge graph has become a term that is recently ubiquitously used in medical, education, finance, e-commerce and other industries to promote artificial intelligence (AI), which evolves from perceptual intelligence to cognitive intelligence. As a branch of knowledge engineering, a knowledge graph is based on the semantic network of knowledge engineering, and it combines the latest advancements achieved in machine learning, natural language processing, knowledge representation, and inference. Both academia and industries are showing keen interest in AI, and several studies are in progress under promotion of big data. With its powerful semantic processing and open interconnection capabilities, the knowledge graph can break the data isolation in different scenarios, and can generate application value in intelligent information services such as intelligent search and recommendation, intelligent question answering, and content distribution networks, thereby making information services more intelligent. The state of the art of knowledge graph technologies is outlined by introducing a process of building a knowledge graph. A knowledge graph is a structured representation of facts, consisting of entities, relations and semantic descriptions. A comprehensive summary of the overall lifecycle technologies of the knowledge graph is provided, including knowledge extraction, knowledge fusion, knowledge reasoning, and knowledge application. But the focus is on knowledge fusion and knowledge reasoning. Entities, relations, attributes, and other knowledge elements can be extracted from existing structured, semi-structured, unstructured data sources, and websites given in encyclopedia using knowledge extraction. With knowledge fusion, the ambiguity between referential items such as entities, relations, and attributes can be eliminated, and a series of basic facts can be obtained. The final knowledge base is formed through ontology extraction, knowledge reasoning and quality evaluation. Following the three steps of knowledge extraction, knowledge fusion, and knowledge reasoning, it can iteratively update the knowledge graph and realize full process automation knowledge acquisition, such as realizing the automatic extraction, automatic association and fusion, automatic processing of fragmented Internet knowledge, and realizing automatic linking of entries and auxiliary functions of entry editing. Finally, the future directions and possible challenges of the knowledge graph are discussed.
-
表 1 部分基于表示學習的知識推理模型
Table 1. Some knowledge reasoning models based on representation learning
Method Scoring function The entity representations The relation representation TransE $ - {\left\| {h + t - r} \right\|_{1/2}}$ $h,t \in {{\mathbb{R}}^d}$ $r \in {{\mathbb{R}}^d}$ ManifoldE $ - {\left( {\left\| {h + t - r} \right\|_2^2 - \theta _r^2} \right)^2}$ $h,t \in {{\mathbb{R}}^d}$ $r \in {{\mathbb{R}}^d}$ SimplE $\dfrac{1}{2}\left( {\left\langle {{h_{{e_i}}},{v_r},{t_{{e_j}}}} \right\rangle + \left\langle {{h_{{e_j}}},{v_{{r^{ - 1}}}},{t_{{e_i}}}} \right\rangle } \right)$ ${h_e},{t_e} \in {{\mathbb{R}}^d}$ ${v_r} \in {{\mathbb{R}}^d}$ RotatE $\left\| {h \circ r - t} \right\|$ $h,t \in {{\mathbb{C}}^d}$ $r \in {{\mathbb{C}}^d}$ QuatE $h \otimes \dfrac{r}{{\left| r \right|}} \cdot t$ $h,t \in {{\rm H}^d}$ $r \in {{\rm H}^d}$ RESCAL ${h^{\rm{T}}}{M_r}t$ $h,t \in {{\mathbb{R}}^d}$ ${M_r} \in {{\mathbb{R}}^{d \times d}}$ DistMult ${h^{\rm{T}}}{\rm{diag}}\left( r \right)t$ $h,t \in {{\mathbb{R}}^d}$ $r \in {{\mathbb{R}}^d}$ ComplEx ${\rm{Re}} \left( {{h^{\rm{T}}}{\rm{diag}}\left( r \right)\bar t} \right)$ $h,t \in {{\mathbb{C}}^d}$ $r \in {{\mathbb{C}}^d}$ ANALOGY ${h^{\rm{T}}}{M_{\rm{r}}}t$ $h,t \in {{\mathbb{R}}^d}$ ${M_r} \in {{\mathbb{R}}^{d \times d}}$ CrossE $\sigma \left( {{\rm{tanh}}\left( {{c_{\rm{r}}} \circ h + {c_{\rm{r}}} \circ h \circ r + b} \right){t^{\rm{T}}}} \right)$ $h,t \in {{\mathbb{R}}^d}$ $r \in {{\mathbb{R}}^d}$ 
下載: 導出CSV
表 2 4類知識推理方法對比
Table 2. Comparisons of 4 kinds of knowledge reasoning methods
Reasoning methods Advantage Disadvantage Typical model Knowledge reasoning based on graph structure and statistical rule mining The advantages of graph structure and rules can significantly improve the accuracy of knowledge reasoning Large-scale knowledge graphs have complex graph structures and rules are not easy to obtain; noise rules can mislead
knowledge reasoningPRA AMIE TensoLog Knowledge reasoning based on representation learning Simple and efficient, suitable for
large-scale knowledge graphDoes not consider the deeper information in the knowledge graph, which limits its accuracy of reasoning RESCAL TransE Knowledge reasoning based on
the neural networkOutstanding learning ability and
reasoning abilityHigh complexity, huge number of parameters, and poor interpretability NTN Knowledge reasoning based
on hybrid methodsCombines the advantages of several
inference methods, so its performance
is excellentMost methods are just shallow fusion,
not taking full advantage of their
respective methodsTKGE
下載: 導出CSV
www.77susu.com<span id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> <span id="fpn9h"><noframes id="fpn9h"> <th id="fpn9h"></th> <strike id="fpn9h"><noframes id="fpn9h"><strike id="fpn9h"></strike> <th id="fpn9h"><noframes id="fpn9h"> <span id="fpn9h"><video id="fpn9h"></video></span> <ruby id="fpn9h"></ruby> <strike id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> -
參考文獻
[1] Sheth A, Thirunarayan K. Semantics Empowered Web 3.0: Managing Enterprise, Social, Sensor, and Cloud-Based Data and Services for Advanced Applications. Vermont: Morgan & Claypool, 2012 [2] Singhal A. Official Google Blog: Introducing the Knowledge Graph: things, not strings[J/OL]. Google Inc (2012-05-02)[2020-02-28]. http://googleblog.blogspot.pt/2012/05/introducing-knowledge-graph-things-not.html [3] Hoffart J, Suchanek F M, Berberich K, et al. YAGO2: a spatially and temporally enhanced knowledge base from Wikipedia. Artif Intelligence, 2013, 194: 28 doi: 10.1016/j.artint.2012.06.001 [4] Auer S, Bizer C, Kobilarov G, et al. DBpedia: a nucleus for a web of open data // Proceedings of the 6th International The Semantic Web and 2nd Asian Conference on Asian Semantic Web Conference. Busan, 2007: 722 [5] Bollacker K, Evans C, Paritosh P, et al. Freebase: a collaboratively created graph database for structuring human knowledge // Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data. Vancouver, 2008: 1247 [6] Carlson A, Betteridge J, Kisiel B, et al. Toward an architecture for never-ending language learning // Twenty-Fourth AAAI Conference on Artificial Intelligence. Atlanta, 2010: 1306 [7] Wu W T, Li H S, Wang H X, et al. Probase: A probabilistic taxonomy for text understanding // Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data. Scottsdale, 2012: 481 [8] Peak Labs. About OpenKG. CN[EB/OL]. Professional Committee of Language and Knowledge Computing, Chinese information Processing Society of China(2018-06-01)[2020-02-28]. http://wp.openkg.cn/?page_id=77PeakLabs關于OpenKG. CN[EB/OL]. 中國中文信息學會語言與知識計算專業委員會(2018-06-01)[2020-02-28]. http://wp.openkg.cn/?page_id=77PeakLabs [9] Xu B, Xu Y, Liang J Q, et al. CN-DBpedia: a never-ending Chinese knowledge extraction system // Proceedings of the 30th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems. Arras, 2017: 428 [10] Niu X, Sun X R, Wang H F, et al. Zhishi. me-weaving Chinese linking open data // Proceedings of the 10th International Semantic Web Conference. Bonn, 2011: 205 [11] Liu Q, Li Y, Duan H, et al. Knowledge graph construction techniques. J Comput Res Dev, 2016, 53(3): 582劉嶠, 李楊, 段宏, 等. 知識圖譜構建技術綜述. 計算機研究與發展, 2016, 53(3):582 [12] Xu Z L, Sheng Y P, He L R, et al. Review on knowledge graph techniques. J Univ Electron Sci Technol China, 2016, 45(4): 589徐增林, 盛泳潘, 賀麗榮, 等. 知識圖譜技術綜述. 電子科技大學學報, 2016, 45(4):589 [13] Qi G L, Gao H, Wu T X. The research advances of knowledge graph. Technol Intelligence Eng, 2017, 3(1): 4漆桂林, 高桓, 吳天星. 知識圖譜研究進展. 情報工程, 2017, 3(1):4 [14] Guan S P, Jin X L, Jia Y T, et al. Knowledge reasoning over knowledge graph: A survey. J Software, 2018, 29(10): 2966官賽萍, 靳小龍, 賈巖濤, 等. 面向知識圖譜的知識推理研究進展. 軟件學報, 2018, 29(10):2966 [15] Huang H Q, Yu J, Liao X, et al. Review on knowledge graphs. Comput Syst Appl, 2019, 28(6): 1黃恒琪, 于娟, 廖曉, 等. 知識圖譜研究綜述. 計算機系統應用, 2019, 28(6):1 [16] Xiao Y H. Knowledge Graph: Concepts and Techniques. Beijing: Publishing House of Electronics Industry, 2020肖仰華. 知識圖譜: 概念與技術. 北京: 電子工業出版社, 2020 [17] Wang H F, Qi G L, Chen H J. Knowledge Graph: Methodology, Practice and Application. Beijing: Publishing House of Electronics Industry, 2019王昊奮, 漆桂林, 陳華鈞. 知識圖譜: 方法、實踐與應用. 北京: 電子工業出版社, 2019 [18] Yan S, Wei K, Hong W F. Knowledge Graph: Technology and Application. Beijing: Posts & Telecom Press, 2019閆樹, 魏凱, 洪萬福. 知識圖譜技術與應用. 北京: 人民郵電出版社, 2019 [19] Zhao J, Liu K, Zhou G Y, et al. Open information extraction. J Chin Inform Process, 2011, 25(6): 98趙軍, 劉康, 周光有, 等. 開放式文本信息抽取. 中文信息學報, 2011, 25(6):98 [20] Quimbaya A P, Munera A S, Rivera R A G, et al. Named entity recognition over electronic health records through a combined dictionary-based approach. Procedia Comput Sci, 2016, 100: 55 doi: 10.1016/j.procs.2016.09.123 [21] Liu X H, Zhang S D, Wei F R, et al. Recognizing named entities in tweets // Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. Association for Computational Linguistics. Portland, 2011: 359 [22] Jain A, Pennacchiotti M. Open entity extraction from web search query logs // Proceedings of the 23rd International Conference on Computational Linguistics. Beijing, 2010: 510 [23] Zhang S D, Elhadad N. Unsupervised biomedical named entity recognition: Experiments with clinical and biological texts. J Biomed Informatics, 2013, 46(6): 1088 doi: 10.1016/j.jbi.2013.08.004 [24] Liu K B, Li F, Liu L, et al. Implementation of a kernel-based Chinese relation extraction system. J Comput Res Dev, 2007, 44(8): 1406 doi: 10.1360/crad20070818劉克彬, 李芳, 劉磊, 等. 基于核函數中文關系自動抽取系統的實現. 計算機研究與發展, 2007, 44(8):1406 doi: 10.1360/crad20070818 [25] Sun L, Han X P. A feature-enriched tree kernel for relation extraction // Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, 2014: 61 [26] Sun A, Grishman R. Active learning for relation type extension with local and global data views // Proceedings of the 21st ACM International Conference on Information and Knowledge Management, New York, 2012: 1105 [27] Fu L S, Grishman R. An efficient active learning framework for new relation types // Proceedings of the Sixth International Joint Conference on Natural Language Processing (IJCNLP). Nagoya, 2013: 692 [28] Ji G L, Liu K, He S Z, et al. Distant supervision for relation extraction with sentence-level attention and entity descriptions // 31st AAAI Conference on Artificial Intelligence. San Francisco, 2017: 3060 [29] Feng J, Huang M L, Zhao L, et al. Reinforcement learning for relation classification from noisy data // 32nd AAAI Conference on Artificial Intelligence. New Orleans, 2018: 5779 [30] Sun T T, Zhang C H, Ji Y, et al. Reinforcement learning for distantly supervised relation extraction. IEEE Access, 2019, 7: 98023 doi: 10.1109/ACCESS.2019.2930340 [31] Wu F, Weld D S. Autonomously semantifying Wikipedia // Proceedings of the Sixteenth ACM Conference on Information and Knowledge Management. Lisbon, 2007: 41 [32] Chang K W, Yih W T, Yang B S, et al. Typed tensor decomposition of knowledge bases for relation extraction // 2014 Conference on Empirical Methods in Natural Language Processing. Doha, 2014: 1568 [33] Zhao X J, Jia Y, Li A P, et al. Multi-source knowledge fusion: A survey // 2019 IEEE Fourth International Conference on Data Science in Cyberspace (DSC). Hangzhou, 2019: 119 [34] Dong X L, Gabrilovich E, Heitz G, et al. From data fusion to knowledge fusion. Proc VLDB Endowment, 2014, 7(10): 881 doi: 10.14778/2732951.2732962 [35] Han X P, Zhao J. Named entity disambiguation by leveraging wikipedia semantic knowledge // Proceedings of the 18th ACM Conference on Information and Knowledge Management. Hong Kong, 2009: 215 [36] Sen P. Collective context-aware topic models for entity disambiguation // Proceedings of the 21st International Conference on World Wide Web. New York, 2012: 729 [37] Guo Z C, Barbosa D. Robust named entity disambiguation with random walks. Semantic Web, 2018, 9(4): 459 doi: 10.3233/SW-170273 [38] Zhu G G, Iglesias C A. Exploiting semantic similarity for named entity disambiguation in knowledge graphs. Expert Syst Appl, 2018, 101: 8 doi: 10.1016/j.eswa.2018.02.011 [39] Shen W, Wang J Y, Luo P, et al. Linden: linking named entities with knowledge base via semantic knowledge // Proceedings of the 21st International Conference on World Wide Web. New York, 2012: 449 [40] Ratinov L A, Roth D, Downey D, et al. Local and global algorithms for disambiguation to Wikipedia // Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. Portland, 2011: 1375 [41] Alokaili A, Menai M E B. SVM ensembles for named entity disambiguation. Computing, 2020, 102(4): 1051 doi: 10.1007/s00607-019-00748-x [42] Agarwal P, Str?tgen J, Del Corro L, et al. DiaNED: time-aware named entity disambiguation for diachronic corpora // Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Melbourne, 2018: 686 [43] Dong X L. Challenges and innovations in building a product knowledge graph // Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, 2018: 2869 [44] Su J L, Wang Y Z, Jin X L, et al. Entity alignment method based on adaptive attribute selection. J Shandong Univ Eng Sci, 2020, 50(1): 14蘇佳林, 王元卓, 靳小龍, 等. 自適應屬性選擇的實體對齊方法. 山東大學學報: 工學版, 2020, 50(1):14 [45] Cheng T, Lauw H W, Paparizos S. Entity synonyms for structured web search. IEEE Trans Knowl Data Eng, 2012, 24(10): 1862 doi: 10.1109/TKDE.2011.168 [46] Pantel P, Crestan E, Borkovsky A, et al. Web-scale distributional similarity and entity set expansion // Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2-Volume 2. Stroudsburg, 2009: 938 [47] Chakrabarti K, Chaudhuri S, Cheng T, et al. A framework for robust discovery of entity synonyms // Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Beijing, 2012: 1384 [48] Mudgal S, Li H, Rekatsinas T, et al. Deep learning for entity matching: a design space exploration // Proceedings of the 2018 International Conference on Management of Data. Houston, 2018: 19 [49] Sun Z Q, Hu W, Zhang Q H, et al. Bootstrapping entity alignment with knowledge graph embedding // Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI). Stockholm, 2018: 4396 [50] Guan S P, Jin X L, Wang Y Z, et al. Self-learning and embedding based entity alignment. Knowl Inform Syst, 2019, 59(2): 361 doi: 10.1007/s10115-018-1191-0 [51] Zhang Q H, Sun Z Q, Hu W, et al. Multi-view knowledge graph embedding for entity alignment // Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI). Macao, 2019: 5429 [52] Zhuang Y, Li G L, Feng J H. A survey on entity alignment of knowledge base. J Comput Res Dev, 2016, 53(1): 165莊嚴, 李國良, 馮建華. 知識庫實體對齊技術綜述. 計算機研究與發展, 2016, 53(1):165 [53] Deshpande O, Lamba D S, Tourn M, et al. Building, maintaining, and using knowledge bases: a report from the trenches // Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data. New York, 2013: 1209 [54] Trisedya B D, Qi J Z, Zhang R. Entity alignment between knowledge graphs using attribute embeddings // Proceedings of the AAAI Conference on Artificial Intelligence. Honolulu, 2019: 297 [55] Chen M H, Tian Y T, Chang K W, et al. Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment // Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}. Stockholm, 2018: 3998 [56] Cao Y X, Liu Z Y, Li C J, et al. Multi-channel graph neural network for entity alignment // Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, 2019: 1452 [57] Lu R, Cai Z P, Zhao S. A survey of knowledge reasoning based on KG. IOP Conf Ser Mater Sci Eng, 2019, 569(5): 052058 [58] Lao N, Cohen W W. Relational retrieval using a combination of path-constrained random walks. Mach Learn, 2010, 81(1): 53 doi: 10.1007/s10994-010-5205-8 [59] Wang Q, Liu J, Luo Y F, et al. Knowledge base completion via coupled path ranking // Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Berlin, 2016: 1308 [60] Xiong W H, Hoang T, Wang W Y. DeepPath: a reinforcement learning method for knowledge graph reasoning // Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Denmark, 2017: 575 [61] Cohen W W. Tensorlog: A differentiable deductive database[J/OL]. arXiv preprint (2016-07-19)[2020-02-28]. https://arxiv.org/abs/1605.06523 [62] Yang F, Yang Z, Cohen W W. Differentiable learning of logical rules for knowledge base reasoning // 31st Conference on Neural Information Proceeding Systems. Long Beach, 2017: 2319 [63] Kampffmeyer M, Chen Y B, Liang X D, et al. Rethinking knowledge graph propagation for zero-shot learning // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, 2019: 11487 [64] Bordes A, Usunier N, Garcia-Duran A, et al. Translating embeddings for modeling multi-relational data // Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2. Lake Tahoe, 2013: 2787 [65] Wang Z, Zhang J W, Feng J L, et al. Knowledge graph embedding by translating on hyperplanes // Twenty-Eighth AAAI Conference on Artificial Intelligence. Québec, 2014: 1112 [66] Lin Y K, Liu Z Y, Sun M S, et al. Learning entity and relation embeddings for knowledge graph completion // Twenty-Ninth AAAI Conference on Artificial Intelligence. Austin, 2015: 2181 [67] Xiao H, Huang M L, Yu H, et al. From one point to a manifold: orbit models for knowledge graph embedding[J/OL]. arXiv preprint (2017-06-17)[2020-02-28]. https://arxiv.org/abs/1512.04792v5 [68] Feng J, Huang M L, Wang M D, et al. Knowledge graph embedding by flexible translation // Fifteenth International Conference on Principles of Knowledge Representation and Reasoning. Palo Alto, 2016: 557 [69] Kazemi S M, Poole D. Simple embedding for link prediction in knowledge graphs // Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal, 2018: 4289 [70] Ebisu T, Ichise R. Toruse: Knowledge graph embedding on a lie group // The Thirty-Second AAAI Conference on Artificial Intelligence. Louisiana, 2018: 1819 [71] Xu C R, Li R J. Relation embedding with dihedral group in knowledge graph // Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, 2019: 263 [72] Sun Z Q, Deng Z H, Nie J Y, et al. Rotate: Knowledge graph embedding by relational rotation in complex space[J/OL]. arXiv preprint (2019-02-26)[2020-02-28]. https://arxiv.org/pdf/1902.10197.pdf [73] Zhang S, Tay Y, Yao L N, et al. Quaternion knowledge graph embeddings // Thirty-third Conference on Neural Information Processing Systems. Vancouver, 2019: 2735 [74] Nickel M, Tresp V, Kriegel H P. A three-way model for collective learning on multi-relational data // The 28th International Conference on Machine Learning The International Conference on Machine Learning. Bellevue, Washington, 2011: 809 [75] Yang B S, Yih W T, He X D, et al. Embedding entities and relations for learning and inference in knowledge bases[J/OL]. arXiv preprint (2015-08-29)[2020-02-28]. http://arxiv.org/abs/1412.6575 [76] Trouillon T, Welbl J, Riedel S, et al. Complex embeddings for simple link prediction // Proceedings of the 33rd International Conference on Machine Learning (ICML). New York City, NY, USA, 2016: 2071 [77] Liu H X, Wu Y X, Yang Y M. Analogical inference for multi-relational embeddings // Proceedings of the 34th International Conference on Machine Learning. Sydney, 2017: 2168 [78] Balazevic I, Allen C, Hospedales T M. TuckER: Tensor factorization for knowledge graph completion // Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, 2019: 5184 [79] Kristiadi A, Khan M A, Lukovnikov D, et al. Incorporating literals into knowledge graph embeddings[J/OL]. arXiv preprint (2019-07-18)[2020-02-28]. https://arxiv.org/abs/1802.00934 [80] Zhang W, Paudel B, Zhang W, et al. Interaction embeddings for prediction and explanation in knowledge graphs // Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining (WSDM). Melbourne, 2019: 96 [81] Socher R, Chen D Q, Manning C D, et al. Reasoning with neural tensor networks for knowledge base completion // Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 1. Nevada, 2013: 926 [82] Neelakantan A, Roth B, McCallum A. Compositional vector space models for knowledge base inference[J/OL]. arXiv preprint (2015-05-27)[2020-02-28]. https://arxiv.org/abs/1504.06662 [83] Das R, Neelakantan A, Belanger D, et al. Chains of reasoning over entities, relations, and text using recurrent neural networks // Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1. Valencia, 2017: 132 [84] Graves A, Wayne G, Reynolds M, et al. Hybrid computing using a neural network with dynamic external memory. Nature, 2016, 538(7626): 471 doi: 10.1038/nature20101 [85] Dettmers T, Minervini P, Stenetorp P, et al. Convolutional 2D knowledge graph embeddings // Thirty-Second AAAI Conference on Artificial Intelligence. New Orleans, 2018: 1811 [86] Vashishth S, Sanyal S, Nitin V, et al. InteractE: improving convolution-based knowledge graph embeddings by increasing feature interactions// Proceedings of the AAAI Conference on Artificial Intelligence, New York, 2020: 3009 [87] Guo S, Ding B Y, Wang Q, et al. Knowledge base completion via rule-enhanced relational learning // China Conference on Knowledge Graph and Semantic Computing. Beijing, 2016: 219 [88] Lu K, Zhang S, Stone P, et al. Robot representation and reasoning with knowledge from reinforcement learning[J/OL]. arXiv preprint (2018-11-22)[2020-02-28]. http://arxiv.org/pdf/1809.11074.pdf [89] Xie R B, Liu Z Y, Jia J, et al. Representation learning of knowledge graphs with entity descriptions // Thirtieth AAAI Conference on Artificial Intelligence. Arizona, 2016: 2659 [90] Wang H. ReNN: Rule-embedded neural networks // 24th International Conference on Pattern Recognition. Beijing, 2018: 824 [91] Zhang W, Paudel B, Wang L, et al. Iteratively learning embeddings and rules for knowledge graph reasoning // The World Wide Web Conference. San Francisco, 2019: 2366 [92] Nie B L, Sun S Q. Knowledge graph embedding via reasoning over entities, relations, and text. Future Generat Comput Syst, 2019, 91: 426 doi: 10.1016/j.future.2018.09.040 [93] Guan N N, Song D D, Liao L J. Knowledge graph embedding with concepts. Knowl Based Syst, 2019, 164: 38 doi: 10.1016/j.knosys.2018.10.008 [94] Mendes P N, Mühleisen H, Bizer C. Sieve: linked data quality assessment and fusion // Proceedings of the 2012 Joint EDBT/ICDT Workshops. Berlin, 2012: 116 [95] Fader A, Soderland S, Etzioni O. Identifying relations for open information extraction // Proceedings of the Conference on Empirical Methods in Natural Language Processing. Edinburgh, 2011: 1535 [96] Dong X, Gabrilovich E, Heitz G, et al. Knowledge vault: a web-scale approach to probabilistic knowledge fusion // Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, 2014: 601 [97] Tan C H, Agichtein E, Ipeirotis P, et al. Trust, but verify: predicting contribution quality for knowledge base construction and curation // Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York, 2014: 553 [98] Wang J, Wang Z Y, Zhang D W, et al. Combining knowledge with deep convolutional neural networks for short text classification // Proceedings of the 26th International Joint Conference on Artificial Intelligence. Melbourne, 2017: 2915 [99] Logan I R L, Liu N F, Peters M E, et al. Barack's wife hillary: Using knowledge-graphs for fact-aware language modeling // The 57th Annual Meeting of the Association for Computational Linguistics. Florence, 2019: 5962 [100] Bauer L, Wang Y C, Bansal M. Commonsense for generative multi-hop question answering tasks // Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, 2018: 4220 [101] Zhu Z K, Zhang P J, Jia Y H, et al. Chinese knowledge base question answering based on multi-label strategy. Comput Eng, https://doi.org/10.19678/j.issn.1000-3428.0056763朱宗奎, 張鵬舉, 賈永輝, 等. 基于多標簽策略的中文知識圖譜問答研究. 計算機工程, https://doi.org/10.19678/j.issn.1000-3428.0056763 [102] Wang X, He X N, Cao Y X, et al. KGAT: Knowledge graph attention network for recommendation // Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Anchorage, 2019: 950 [103] Ji S X, Pan S R, Cambria E, et al. A survey on knowledge graphs: representation, acquisition and applications[J/OL]. arXiv preprint (2020-02-02)[2020-02-28]. http://arxiv.org/abs/2002.00388 [104] Ji Y C. Welcome to Magi[EB/OL]. Peak Labs (2019-08-20)[2020-02-28]. https://www.peak-labs.com/docs/en/magi/intro -
點擊查看大圖
圖(1) / 表(2)
計量
- 文章訪問數: 6199
- HTML全文瀏覽量: 2640
- PDF下載量: 748
- 被引次數: 0
