知识图谱问题生成任务是从给定的知识图谱中生成与其相关的问题。目前,知识图谱问题生成模型主要使用基于RNN或Transformer对知识图谱子图进行编码,但这种方式丢失了显式的图结构化信息,在解码器中忽视了局部信息对节点的重要性。该文提出用迭代信息传递图编码器来编码子图,获取子图显式的图结构化信息,此外,该文采用滑动窗口层次注意力机制学习子图局部信息对节点的重要度。从WebQuestions和PathQuestions数据集上的实验结果看,该文提出的模型比KTG模型在BLEU-4指标上分别高出2.16和15.44,证明了该模型的有效性。
Abstract
Knowledge graph question generation task is to generate related questions from a given knowledge graph. In recent years, knowledge graph problem generation models mainly use RNN or Transformer to encode the knowledge graph subgraph, ignoring the explicit graph structure. We propose an Iterative Message Passing graph encoder to encode subgraph and capture the explicit structured information of subgraph. In addition, we use the Sliding-Window Hierarchical Attention mechanism to learn the importance of the local information of the subgraph to nodes. Experiments on WebQuestions and PathQuestions datasets indicate that our model outperforms KTG model by 2.16 and 15.44 respectively, in terms of BLEU-4 metric, which verify the effectiveness of proposed model.
关键词
知识图谱 /
问题生成 /
图神经网络
{{custom_keyword}} /
Key words
knowledge graph /
question generation /
graph neural network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] DU X, SHAO J, CARDIE C. Learning to ask: Neural question generation for reading comprehension[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1342-1352.
[2] SONG L, WANG Z, HAMZA W, et al. Leveraging context information for natural question generation[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,2018: 569-574.
[3] LI Y, DUAN N, ZHOU B, et al. Visual question generation as dual task of visual question answering[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018:6116-6124.
[4] BAO J, TANG D, DUAN N, et al. Table-to-text: Describing table region with natural language[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018: 5020-5027.
[5] SEYLER D, YAHYA M, KLAUS. B. Knowledge questions from knowledge graphs[C]//Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval,2017: 11-18.
[6] KUMAR V, HUA Y, RAMAKRISHNAN G, et al. Difficulty-controllable multi-hop question generation from knowledge graphs[C]//Proceedings of International Semantic Web Conference, 2019: 382-398.
[7] BI S, CHENG X, LI Y F, et al. Knowledge-enriched, type-constrained and grammar-guided question generation over knowledge bases[J]. arXiv preprint arXiv:2010.03157v3,2020.
[8] SERBAN I V, GARCIADURN A, GULCEHRE C, et al. Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 307-317.
[9] ELSAHAR H, GRAVIER C, LAFOREST F. Zero-shot question generation from knowledge graphs for unseen predicates and entity types[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics,2018: 1639-1649.
[10] LIU C, LIU K, HE S, et al. Generating questions for knowledge bases via incorporating diversified contexts and answer-aware loss[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 2431-2441.
[11] CHEN Y, WU L, ZAKI M J. Toward subgraph guided knowledge graph question generation with graph neural networks[J].arXiv preprint arXiv:2004. 06015, 2020e.
[12] SEYLER D, YAHYA M, BERBERICH K.Generating quiz questions from knowledge graphs[C]//Proceedings of International Conference on World Wide Web, 2015: 113-114.
[13] SONG L, ZHAO L. Question generation from a knowledge base with web exploration[J]//arXiv preprint arXiv:1610.03807, 2016.
[14] INDURTHI S R, RAGHU D, KHAPRA M.Generating natural language question-answer pairs from a knowledge graph using a rnn based question generation mode[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017: 376-385.
[15] XU D, ZHU Y, CHOY C B, et al. Cene Graph generation by iterative message passing[C]//Proceedings of IEEE Computer Society,2017: 113-122.
[16] PENNINGTON J, SOCHER R, MANNING C.Glove: Global vectors for word representation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2014: 1532-1543.
[17] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735- 1780.
[18] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017,10(7): 5998-6008.
[19] KLEIN G, KIM Y, DENG Y, et al. OpenNMT: Open-source toolkit for neural machine translation[C]//Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2017: 135-142.
[20] YIH W, RICHARDSON M, MEEK C, et al. The value of semantic parse labeling for knowledge base question answering[C]//Proceedings of the Association for Computational Linguistics, 2016: 201-206.
[21] TALMOR A, BERANT J. The web as a knowledge-base for answering complex questions[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,2018: 336-345.
[22] ZHOU M, HUANG M, ZHU X. An interpretable reasoning network for multi-relation question answering[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018: 2010-2022.
[23] KISHORE P, SALIM R, TODD W, el al.Bleu: A method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting on Association for Computational Linguistics,2002: 311-318.
[24] BANERJEE S, LAVIE A. Meteor:An automatic metric for mt evaluation with improved correlation with human judgments[C]//Proceedings of the acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, 2005: 65-72.
[25] LIN C Y. Rouge: A package for automatic evaluation of summaries[C]//Proceedings of the ACL Workshop,2004: 74-81.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
山西省自然科学基金(202203021221021,202203021221001,20210302123468,201901D111032);国家自然科学基金(62076158)
{{custom_fund}}
PDF(2416 KB)
