计算机科学 ›› 2023, Vol. 50 ›› Issue (3): 12-22.doi: 10.11896/jsjkx.220700111
• 知识图谱赋能的知识工程:理论、技术与系统专题 • 上一篇 下一篇
马廷淮1, 孙圣杰1, 荣欢2, 钱敏峰1
MA Tinghuai1, SUN Shengjie1, RONG Huan2, QIAN Minfeng1
摘要: 知识图谱转译文本(Graph-to-Text)是知识图谱领域中一个新的任务,旨在将知识图谱转化为描述该知识的可读性文本。随着近年来研究的不断深入,知识图谱转译文本的生成技术已经被应用于商品评论生成、推荐解释生成、论文摘要生成等领域。现有方法中的转译模型均采用先规划后实现的方式,未能根据已生成文本动态调整规划且未按静态内容规划对知识进行跟踪,导致文本前后语义不连贯。为了提高生成文本语义的连贯性,文中提出了基于动态记忆和双层重构强化的知识图谱至文本转译模型,通过静态内容规划、动态内容规划和双层重构机制这3个阶段,弥补了知识图谱与文本之间的结构化差异,在生成文本的同时侧重关注各三元组中的重要内容。与现有的生成模型相比,该模型不仅能缓解知识图谱与文本之间的结构化差异,还提高了定位关键实体的能力,从而使生成的文本具有更强的事实一致性和语义连贯性。在WebNLG数据集上进行了广泛实验,结果表明,在知识图谱转译文本的任务上,所提模型与现有模型相比,内容规划更加准确,生成文本语句间的逻辑合理且关联性更强,在BLEU,METEOR,ROUGE,CHRF++等指标上优于现有模型。
中图分类号:
[1]JI S,PAN S,CAMBRIA E,et al.A survey on knowledgegraphs:Representation,acquisition,and applications[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(2):494-514. [2]LIU Q,LI Y,DUAN H,et al.Knowledge Graph Construction Techniques[J].Journal of Computer Research and Development,2016,53(3):582-600. [3]WYLOT M,HAUSWIRTH M,CUDRÉ-MAUROUX P,et al.RDF data storage and query processing schemes:A survey[J].ACM Computing Surveys(CSUR),2018,51(4):1-36. [4]PUDUPPULLY R,DONG L,LAPATA M.Data-to-text generation with content selection and planning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:6908-6915. [5]ZHANG X B,GONG H G,YANG F,et al.Chinese sentence-level lip reading based on end-to-end model[J].Journal of Software,2020,31(6):1747-1760. [6]XU F,LUO J,WANG M,et al.Speech-driven end-to-end language discrimination toward chinese dialects[J].ACM Transactions on Asian and Low-Resource Language Information Processing(TALLIP),2020,19(5):1-24. [7]GARDENT C,SHIMORINA A,NARAYAN S,et al.TheWebNLG challenge:Generating text from RDF data[C]//Proceedings of the 10th International Conference on Natural Language Generation.2017:124-133. [8]WISEMAN S J,SHIEBER S M,RUSH A S M.Challenges in Data-to-Document Generation[C]//Proceedings of the Confe-rence on Empirical Methods in Natural Language Processing(EMNLP2017).Association for ComputationalLinguistics,2017. [9]KUKICH K.Design of a knowledge-based report generator[C]//21st Annual Meeting of the Association for Computa-tional Linguistics.1983:145-150. [10]BAO J,TANG D,DUAN N,et al.Table-to-text:Describing table region with natural language[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018. [11]BANARESCU L,BONIAL C,CAI S,et al.Abstract meaning representation for sembanking[C]//Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse.2013:178-186. [12]DISTIAWAN B,QI J,ZHANG R,et al.GTR-LSTM:A triple encoder for sentence generation from RDF data[C]//Procee-dings of the 56th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).2018:1627-1637. [13]LI W,PENG R,WANG Y,et al.Knowledge graph based natural language generation with adapted pointer-generator networks[J].Neurocomputing,2020,382(1):174-187. [14]CHEN W,SU Y,YAN X,et al.KGPT:Knowledge-Grounded Pre-Training for Data-to-Text Generation[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP).2020:8635-8648. [15]GAO H,WU L,HU P,et al.RDF-to-text generation withgraph-augmented structural neural encoders[C]//Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence.2021:3030-3036. [16]XU B B,CEN K T,HUANG J J,et al.A survey on Graph Convolution Neural Network[J].Chinese Journal of Computers,2020,43(5):755-780. [17]GUO Z,ZHANG Y,TENG Z,et al.Densely connected graphconvolutional networks for graph-to-sequence learning[J].Transactions of the Association for Computational Linguistics,2019,7(1):297-312. [18]BECK D,HAFFARI G,COHN T.Graph-to-sequence learning using Gated Graph Neural Networks[C]//Annual Meeting of the Association of Computational Linguistics 2018.Association for Computational Linguistics(ACL).2018:273-283. [19]KONCEL-KEDZIORSKI R,BEKAL D,LUAN Y,et al.TextGeneration from Knowledge Graphs with Graph Transformers[C]//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).2019:2284-2293. [20]SHI Y,LUO Z,ZHU P,et al.G2T:Generating Fluent Descriptions for Knowledge Graph[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:1861-1864. [21]GAO H,WU L,HU P,et al.RDF-to-text generation withgraph-augmented structural neural encoders[C]//Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence.2021:3030-3036. [22]RIBEIRO L F R,ZHANG Y,GARDENT C,et al.Modeling global and local node contexts for text generation from know-ledge graphs[J].Transactions of the Association for Computational Linguistics,2020,8(1):589-604. [23]XU F,DAN Y,YAN K,et al.Low-Resource Language Discrimination toward Chinese Dialects with Transfer Learning and Data Augmentation[J].Transactions on Asian and Low-Resource Language Information Processing,2021,21(2):1-21. [24]RIBEIRO L F R,SCHMITT M,SCHÜTZE H,et al.Investigating Pretrained Language Models for Graph-to-Text Generation[C]//Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI.2021:211-227. [25]KALE M,RASTOGI A.Text-to-Text Pre-Training for Data-to-Text Tasks[C]//Proceedings of the 13th International Confe-rence on Natural Language Generation.2020:97-102. [26]LI J,TANG T,ZHAO W X,et al.Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models[C]//Findings of the Association for Computational Linguistics:ACL-IJCNLP 2021.2021:1558-1568. [27]KURITA K,MICHEL P,NEUBIG G.Weight Poisoning At-tacks on Pretrained Models[C]//Proceedings of the 58th An-nual Meeting of the Association for Computational Linguistics.2020:2793-2806. [28]MIAO N,SONG Y,ZHOU H,et al.Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:3436-3441. [29]FERREIRA T C,VAN DER LEE C,VAN MILTENBURG E,et al.Neural data-to-text generation:A comparison between pipeline and end-to-end architectures[C]//2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Association for Computational Linguistics,2019:552-562. [30]CHU X M,ZHU Q M,ZHOU G D.Discourse Primary-Secon-dary Relationships in Natural Language Processing[J].Chinese Journal of Computers,2017,40(4):842-860. [31]MORYOSSEF A,GOLDBERG Y,DAGAN I.Step-by-Step:Separating Planning from Realization in Neural Data-to-Text Generation[C]//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).2019:2267-2277. [32]ZHAO C,WALKER M,CHATURVEDI S.Bridging the structural gap between encoding and decoding for data-to-text gene-ration[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:2481-2491. [33]PUDUPPULLY R,DONG L,LAPATA M.Data-to-text generation with content selection and planning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:6908-6915. [34]PUDUPPULLY R,LAPATA M.Data-to-text Generation with Macro Planning[J].Transactions of the Association for Computational Linguistics,2021,9(1):510-527. [35]SHAO Z,HUANG M,WEN J,et al.Long and Diverse Text Generation with Planning-based Hierarchical Variational Model[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJC-NLP).2019:3257-3268. [36]SU Y,VANDYKE D,WANG S,et al.Plan-then-Generate:Controlled Data-to-Text Generation via Planning[C]//Findings of the Association for Computational Linguistics:EMNLP 2021.2021:895-909. [37]LEWIS M,LIU Y,GOYAL N,et al.BART:Denoising Se-quence-to-Sequence Pre-training for Natural Language Generation,Translation,and Comprehension[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:7871-7880. [38]CHEN K,LI F,HU B,et al.Neural Data-to-Text Generation with Dynamic Content Planning[J].arxiv:2004.07426,2020. [39]ISO H,UEHARA Y,ISHIGAKI T,et al.Learning to select,track,and generate for data-to-text[J].Journal of Natural Language Processing,2020,27(3):599-626. [40]PUDUPPULLY R,DONG L,LAPATA M.Data-to-text Gene-ration with Entity Modeling[C]//Proceedings of the 57th An-nual Meeting of the Association for Computational Linguistics.2019:2023-2035. [41]SHEN X,CHANG E,SU H,et al.Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:7155-7165. [42]GEHRMANN S,ADEWUMI T,AGGARWAL K,et al.TheGEM Benchmark:Natural Language Generation,its Evaluation and Metrics[C]//1st Workshop on Natural Language Generation,Evaluation,and Metrics 2021.Association for Computational Linguistics,2021:96-120. |
[1] | 刘红, 朱焱, 李春平. 融合多类时空轨迹特征的跨网络用户身份识别 Cross-network User Identification Based on Multiple Spatio-Temporal Trajectory Features 计算机科学, 2023, 50(3): 114-120. https://doi.org/10.11896/jsjkx.211200287 |
[2] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[3] | 王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011 |
[4] | 金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190 |
[5] | 赵冬梅, 吴亚星, 张红斌. 基于IPSO-BiLSTM的网络安全态势预测 Network Security Situation Prediction Based on IPSO-BiLSTM 计算机科学, 2022, 49(7): 357-362. https://doi.org/10.11896/jsjkx.210900103 |
[6] | 康雁, 徐玉龙, 寇勇奇, 谢思宇, 杨学昆, 李浩. 基于Transformer和LSTM的药物相互作用预测 Drug-Drug Interaction Prediction Based on Transformer and LSTM 计算机科学, 2022, 49(6A): 17-21. https://doi.org/10.11896/jsjkx.210400150 |
[7] | 刘宝宝, 杨菁菁, 陶露, 王贺应. 基于DE-LSTM模型的教育统计数据预测研究 Study on Prediction of Educational Statistical Data Based on DE-LSTM Model 计算机科学, 2022, 49(6A): 261-266. https://doi.org/10.11896/jsjkx.220300120 |
[8] | 王杉, 徐楚怡, 师春香, 张瑛. 基于CNN-LSTM的卫星云图云分类方法研究 Study on Cloud Classification Method of Satellite Cloud Images Based on CNN-LSTM 计算机科学, 2022, 49(6A): 675-679. https://doi.org/10.11896/jsjkx.210300177 |
[9] | 王飞, 黄涛, 杨晔. 基于Stacking多模型融合的IGBT器件寿命的机器学习预测算法研究 Study on Machine Learning Algorithms for Life Prediction of IGBT Devices Based on Stacking Multi-model Fusion 计算机科学, 2022, 49(6A): 784-789. https://doi.org/10.11896/jsjkx.210400030 |
[10] | 高堰泸, 徐圆, 朱群雄. 基于A-DLSTM夹层网络结构的电能消耗预测方法 Predicting Electric Energy Consumption Using Sandwich Structure of Attention in Double -LSTM 计算机科学, 2022, 49(3): 269-275. https://doi.org/10.11896/jsjkx.210100006 |
[11] | 潘志豪, 曾碧, 廖文雄, 魏鹏飞, 文松. 基于交互注意力图卷积网络的方面情感分类 Interactive Attention Graph Convolutional Networks for Aspect-based Sentiment Classification 计算机科学, 2022, 49(3): 294-300. https://doi.org/10.11896/jsjkx.210100180 |
[12] | 丁锋, 孙晓. 基于注意力机制和BiLSTM-CRF的消极情绪意见目标抽取 Negative-emotion Opinion Target Extraction Based on Attention and BiLSTM-CRF 计算机科学, 2022, 49(2): 223-230. https://doi.org/10.11896/jsjkx.210100046 |
[13] | 宋美琦, 傅湘玲, 闫晨巍, 仵伟强, 任芸. 基于双向长短时记忆网络的企业弹性能力预测模型 Prediction Model of Enterprise Resilience Based on Bi-directional Long Short-term Memory Network 计算机科学, 2022, 49(11): 197-205. https://doi.org/10.11896/jsjkx.210900195 |
[14] | 王凯, 李舟军, 盛文博, 陈舒玮, 王明轩, 刘剑青, 蓝海波, 张锐. 多轮对话技术及其在电网数据查询中的应用 Multi-turn Dialogue Technology and Its Application in Power Grid Data Query 计算机科学, 2022, 49(10): 265-271. https://doi.org/10.11896/jsjkx.200600078 |
[15] | 姚冬, 李舟军, 陈舒玮, 季震, 张锐, 宋磊, 蓝海波. 面向任务的基于深度学习的多轮对话系统与技术 Task-oriented Dialogue System and Technology Based on Deep Learning 计算机科学, 2021, 48(5): 232-238. https://doi.org/10.11896/jsjkx.200600092 |
|