面向知识库的自动问答是自然语言处理的一项重要任务,其旨在对用户提出的自然语言形式问题给出精练、准确的回复。目前由于缺少数据集,存在特征不一致等因素,导致难以使用通用的数据和方法实现领域知识库问答。因此,该文将“问题意图”视作不同领域问答可能存在的共同特征,将“问题”与三元组知识库中“关系谓词”的映射过程作为问答核心工作。为了考虑多种层次的语义并避免重要信息的损失,该文分别将“基于门控卷积的深层语义”和“基于交互注意力机制的浅层语义”通过门控感知机制相融合。在NLPCC-ICCPOL 2016 KBQA数据集上的实验表明,该文方法与现有的CDSSM和BDSSM方法相比,效能有明显提升。此外,该文通过构造天文常识知识库,将问题与关系谓词映射模型移植到特定领域,结合Bi-LSTM-CRF模型构建了天文常识自动问答系统。
Abstract
Knowledge Base Question Answer (KBQA) is a natural language processing task to generate refined and accurate responses to natural language questions raised by users. Therefore, this paper treats the question intent identification as the common issue for KBQA of various domains, and the mapping between the question and the predicate of the tuple in the knowledge base as the key issue. Specifically, we combine the "gated convolution for deep semantics" and " interactive attention mechanism for shallow semantics" into a unified framework via the gated perception mechanism. Experiments on NLPCC-ICCPOL 2016 KBQA dataset show that our proposed method significantly outperforms the existing CDSSM and BDSSM. Besides, we adapt our method for a commonsense automatic question answering system via a commonsense knowledge base of astronomy.
关键词
知识库 /
属性映射 /
深层语义
{{custom_keyword}} /
Key words
knowledge base /
property mapping /
deep semantic
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Auer S,Bizer C, Kobilarov G, et al. DBpedia: a nucleus for a web of open data[M]. The Semantic Web. Springer, Berlin, Heidelberg, 2007: 722-735.
[2] Bollacker K, Evans C, Paritosh P, et al. Freebase: a collaboratively created graph database for structuring human knowledge[C]//Proceedings of the ACM SIGMOD International Conference on Management of Data. ACM, 2008: 1247-1250.
[3] Hoffart J, Suchanek F M, Berberich K, et al. YAGO2: exploring and querying world knowledge in time, space, context, and many languages[C]//Proceedings of the 20th International Conference Companion on World Wide Web. ACM, 2011: 229-232.
[4] Vrandecic D, Krotzsch M. WikiData: a free collaborative knowledge base[J]. Communications of the ACM, 2014, 57(10): 78-85.
[5] Dong L,Wei F,Zhou M,etal. 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, 2015: 260-269.
[6] Liang P, Jordan M I, Klein D. Learning dependency based compositional semantics[J]. Computational Linguistics, 2013, 39(2): 389-446.
[7] Berant J, Chou A, Frostig R, et al. Semantic parsing on freebase from question answer pairs[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2013: 1533-1544.
[8] Berant J, Liang P. Semantic parsing via paraphrasing[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014, 1: 1415-1425.
[9] Yao X, VanDurme B. Information extraction over structured data: question answering with freebase[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014, 1: 956-966.
[10] Zettlemoyer L S, Collins M. Learning to map sentences to logical form: structured classification with probabilistic categorial grammars[J]. arXiv preprint arXiv:1207.1420, 2012.
[11] Kwiatkowski T,Zettlemoyer L, Gold water S, et al. Inducing probabilistic CCG grammars from logical form with higher order unification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2010: 1223-1233.
[12] Lai Y, Lin Y, Chen J, et al. Open domain question answering system based on knowledge base[M]. Natural Language Understanding and Intelligent Applications. Springer, Cham, 2016: 722-733.
[13] Wang L, Zhang Y, Liu T. A deep learning approach for question answering over knowledge base[M]. Natural Language Understanding and Intelligent Applications. Springer, Cham, 2016: 885-892.
[14] Yang F,Gan L, Li A, et al. Combining deep learning with information retrieval for question answering[M]. Natural Language Understanding and Intelligent Applications. Springer, Cham, 2016: 917-925.
[15] 周博通,孙承杰,林磊,等. 基于LSTM的大规模知识库自动问答[J]. 北京大学学报(自然科学版), 2018, 54(2): 286-292.
[16] Xie Z, Zeng Z, Zhou G, et al. Topic enhanced deep structured semantic models for knowledge base question answering[J]. Science China: Information Sciences,2017,60(11):28-42.
[17] 赵小虎,赵成龙. 基于多特征语义匹配的知识库问答系统[J]. 计算机应用,2020,40(07):1873-1878.
[18] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 5998-6008.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61972173)
{{custom_fund}}
PDF(5562 KB)
