[1]于皓,张杰,吴明辉,等.领域知识图谱快速构建和应用框架[J].智能系统学报,2021,16(5):871-884.[doi:10.11992/tis.202103024]
YU Hao,ZHANG Jie,WU Minghui,et al.A framework for rapid construction and application of domain knowledge graphs[J].CAAI Transactions on Intelligent Systems,2021,16(5):871-884.[doi:10.11992/tis.202103024]
点击复制
YU Hao,ZHANG Jie,WU Minghui,et al.A framework for rapid construction and application of domain knowledge graphs[J].CAAI Transactions on Intelligent Systems,2021,16(5):871-884.[doi:10.11992/tis.202103024]
领域知识图谱快速构建和应用框架
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第5期
页码:
871-884
栏目:
吴文俊人工智能技术发明奖一等奖
出版日期:
2021-09-05
- Title:
- A framework for rapid construction and application of domain knowledge graphs
- Keywords:
- domain knowledge graph; schema; entity linking; knowledge completion; KBQA; multiple-person cooperation; business experts; technical experts
- 分类号:
- TP391
- 摘要:
- 快速构建和应用领域知识图谱(domain knowledge graphs, DKG)已成为企业的迫切需求。然而，领域知识图谱的快速构建和应用仍然存在问题：1）构建前，复杂领域场景涉及知识维度广，业务专家短时间内难以构建完备的领域schema；2）构建中，业务和技术专家深度耦合，图谱构建缓慢，难以适应业务快速发展需求；3）构建后，图谱应用严重依赖技术人员开发，业务专家无法自主基于领域知识图谱探索问题解决方案。为解决上述问题，本文提出了领域知识图谱的快速构建和应用框架，其中包括：多人协作构建领域schema解决领域知识的复杂性问题，将业务和技术专家解耦合，提高领域知识图谱的构建效率，最后通过建立基于行业schema的auto-KBQA((knowledge base question answering)解决领域知识图谱在知识问答应用的快速落地。通过实际项目的应用落地，验证了该框架可有效加快领域知识图谱的落地应用，期望该框架给领域知识图谱的快速构建和应用带来一定的启发和帮助。
- Abstract:
- There is an urgent need for enterprises to rapidly construct and apply domain knowledge graphs (DKG). However, there are still problems in meeting this need: firstly, extensive knowledge is required to deal with complex domain scenarios and it is difficult for business experts to rapidly construct a complete domain schema; secondly, the construction process is so slow that it’s difficult to meet the needs of rapid business development, because information exchanges are ambiguous between business experts and technical experts; thirdly, after their construction, the heavy dependence of the applications of graphs on technical personnel refrains business experts from exploring approaches to solving business problems. In order to solve the above problems, this paper proposes a framework for the rapid construction and applications of DKG. It builds a domain schema through multiple-person cooperation to solve complex problems and improves the construction efficiency by decoupling business experts and technical experts in the construction and applications of DKG. Finally, it builds the schema-based auto-KBQA((knowledge base question answering) for fast applications of DKG in question and answering mode. Through real-world applications, it is verified that the framework can effectively accelerate the construction and applications of DKG. The framework is expected to bring insights and extend assistance to the rapid construction and application of DKG.
- 参考文献/References:
-
[1] WU Minghui, WU Xindong. On big wisdom[C]//Proceedings of the IEEE International Conference on Data Mining. Singapore, Singapore, 2018:1-2.
[2] NADEAU D, SEKINE S. A survey of named entity recognition and classification[J]. Lingvistic? investigationes, 2007, 30(1): 3–26.
[3] GRISHMAN R, SUNDHEIM B. Message understanding conference-6: a brief history[C]//Proceedings of the 16th Conference on Computational Linguistics. Copenhagen, Denmark, 1996:466-471.
[4] RABINER L R. A tutorial on hidden Markov models and selected applications in speed recognition[J]. Proceedings of IEEE, 1989, 77(2): 257–286.
[5] SEKINE S, GRISHMAN R, SHINNOU H. A decision tree method for finding and classifying names in Japanese texts[C]//Proceedings of the 6th Workshop on Very Large Corpora.Montreal. Quebec, Canada, 1998:171-178.
[6] BORTHWICK A, STERLING J, AGICHTEIN E, et al. NYU: description of the MENE named entity system as used in MUC-7[C]//Proceedings of the 7th Message Understanding Conference. Washington, DC, USA, 1998.
[7] ASAHARA M, MATSUMOTO Y. Japanese named entity extraction with redundant morphological analysis[C]//Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology. Edmonton, Canada, 2003:8-15.
[8] LAFFERTY J D, MCCALLUM A, PEREIRA F C N. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco, CA, United States, 2001: 282-289.
[9] LAMPLE G, BALLESTEROS M, SUBRAMANIAN S, et al. Neural architectures for named entity recognition[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. San Diego, California, USA, 2016: 260-270.
[10] ZHANG Yue, YANG Jie. Chinese NER using lattice LSTM[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia, USA, 2018: 1554-1564.
[11] DEVLIN J, CHANG Mingwei, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Com-putational Linguistics: Human Language Technologies Minneapolis, Minnesota, USA, 2019: 4171-4186.
[12] ZHANG Zhengyan, HAN Xu, LIU Zhiyuan, et al. ERNIE: enhanced language representation with informative entities[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy, 2019: 1441-1451.
[13] LI X, YAN H, QIU X, et al. FLAT: Chinese NER using flat-lattice transformer[C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Seattle, Washington, USA, 2020:6836-6842.
[14] YE Z X, LING Z H. Distant supervision relation extraction with intra-bag and inter-bag attentions[C]// Proceedings of the 2019 Conference of the North. Minneapolis, Minnesota, USA,2019:2810-2819.
[15] QIN Pengda, XU Weiran, WANG W Y. Robust distant supervision relation extraction via deep reinforcement learning[C]// Meeting of the Association for Computational Linguistics. Melbourne, Australia, 2018: 2137-2147
[16] ALT C, HüBNER M, HENNIG L. Fine-tuning pre-trained transformer language models to distantly supervised relation extraction[J]. arXiv preprint arXiv:1906.08646, 2019.
[17] YE Zhixiu, LING Zhenhua. Multi-level matching and aggregation network for few-shot relation classification[J]. arXiv preprint arXiv:1906.06678, 2019.
[18] SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[C]//Proceedings of the 31st Conference on Neural Information Processing Systems. Long Beach, CA, USA, 2007: 4077-4087.
[19] SHEN Wei, WANG Jianyong, HAN Jiawei. Entity linking with a knowledge base: issues, techniques, and solutions[J]. IEEE transactions on knowledge and data engineering, 2015, 27(2): 443-460.
[20] SEVGILI O, SHELMANOV A, ARKHIPOV M, et al. Neural entity linking: a survey of models based on deep learning[J]. arXiv:2006.00575, 2021.
[21] GU Yingjie, QU Xiaoye, WANG Zhefeng, et al. Read, retrospect, select: an MRC framework to short text entity linking[J]. arXiv:2101.02394, 2021.
[22] WU L, PETRONI F, JOSIFOSKI M, et al. Scalable zero-shot entity linking with dense entity retrieval[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. PuntaCana, The Dominican Republic,2020: 6397-6407.
[23] LIN Yankai, LIU Zhiyuan, SUN Maosong, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence. Austin, Texas, 2015: 2181-2187.
[24] SOCHER R, CHEN Danqi, MANNING C D, et al. Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, 2013: 926-934.
[25] WANG Zhen, ZHANG Jianwen, FENG Jianlin, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence. Quebec, Canada, 2014: 1112-1119.
[26] SHI B X, WENINGER T. Open-world knowledge graph completion[C]//Proceedings of the 32nd International Conference on Artificial Intelligence. New Orleans, Louisiana, USA, 2018: 1957-1964.
[27] LAO Ni, COHEN W W. Relational retrieval using a combination of path-constrained random walks[J]. Machine learning, 2010, 81(1): 53-67.
[28] GARDNER M, TALUKDAR P, KRISHNAMURTHY J, et al. Incorporating vector space similarity in random walk inference over knowledge bases[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha, Qatar, 2014: 397-406.
[29] XIONG Wenhan, HOANG T, WANG W Y. DeepPath: a reinforcement learning method for knowledge graph reasoning[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen, Denmark, 2017: 564-573.
[30] XIONG Wenhan, YU Mo, CHANG Shiyu, et al. One-shot relational learning for knowledge graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium, 2018: 1980-1990.
[31] YIH W T, HE Xiaodong, MEEK C. Semantic parsing for single-relation question answering[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, Maryland, 2014: 643-648.
[32] REDDY S, LAPATA M, STEEDMAN M. Large-scale semantic parsing without question-answer pairs[J]. Transactions of the association for computational linguistics, 2014, 2: 377-392.
[33] XU Kun, WU Lingfei, WANG Zhiguo, et al. Exploiting rich syntactic information for semantic parsing with graph-to-sequence model[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium, 2018: 918-924.
[34] BORDES A, USUNIER N, CHOPRA S, et al. Large-scale simple question answering with memory networks[J]. arXiv preprint arXiv:1506.02075, 2015.
[35] DONG Li, WEI Furu, ZHOU Ming, et al. Question answering over freebase with multi-column convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing, China, 2015: 260-269.
[36] ZHANG Yuanzhe, LIU Kang, HE Shizhu, et al. Question answering over knowledge base with neural attention combining global knowledge information[J]. arXiv preprint arXiv:1606.00979, 2016.
[37] ZHANG Yuyu, DAI Hanjun, KOZAREVA Z, et al. Variational reasoning for question answering with knowledge graph[C]//Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence.San Francisco, California, USA, 2018:1-13.
[38] LIN X V, SOCHER R, XIONG Caiming. Multi-hop knowledge graph reasoning with reward shaping[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium, 2018: 3243-3253.
备注/Memo
收稿日期:2021-03-15。
基金项目:国家重点研发计划项目（2016YFB1000901）；国家自然科学基金项目（91746209）；教育部创新团队项目（IRT17R3）；国家发改委项目（20190404165100454）
作者简介:于皓，博士研究生，主要研究方向为机器学习、知识图谱和自然语言处理;张杰，博士研究生，主要研究方向为知识工程、自然语言处理;吴信东，教授，博士生导师，主要研究方向为数据挖掘、大数据分析、知识工程。明略科技集团首席科学家和明略科学院院长，教育部大数据知识工程重点实验室（合肥工业大学）主任，营销智能国家新一代人工智能开放创新平台负责人，国家重点研发计划重点专项项目“大数据知识工程基础理论及其应用研究”首席科学家
通讯作者:吴信东.E-mail:wuxindong@mininglamp.com
更新日期/Last Update:
1900-01-01