面向科技情报分析的知识库构建方法

doi:10.3778/j.issn.1002-8331.2104-0397

摘要/Abstract

摘要： 在知识库构建中，最重要的部分就是提取文本中的三元组，而三元组的提取需要实体抽取和实体关系抽取技术。针对实体抽取提出了一种CWATT-BiLSTM-LSTMd（character word attention-bidirectional long short-term memory-long short-term memory）模型。该模型可以有效解决实体抽取中一词多义问题，并且可以模拟标签的依赖问题。在实体抽取的基础上进行实体关系的抽取，为解决实体关系抽取中远程监督的局限性，提出一种基于强化深度学习的RL-TreeLSTM（reinforcement learning tree long short-term memory）模型。该模型分为选择器和分类器，选择器选择有效的句子传入分类器，分类器对句子中实体对的关系标签进行预测。选择器和分类器共同训练以优化选择和分类过程，可以有效降低远程监督带来的噪音。实验结果表明，提出的模型和方法能有效地提高实体及其关系的抽取性能。

关键词: 知识库构建, 神经网络, 强化学习, 实体抽取, 实体关系抽取

Abstract: In the construction of knowledge base, the most important part is to extract the triplets in the text, and the extraction of triples requires entity extraction and entity relationship extraction techniques. A CWATT-BiLSTM-LSTMd（character word attention-bidirectional long short-term memory-long short-term memory） model for entity extraction is proposed. The model can effectively solve the polysemy problem in entity extraction, and simulate the dependency of the tag. On the basis of entity extraction, entity relationship extraction is performed. To solve the limitation of remote supervision in entity relationship extraction, a RL-TreeLSTM（reinforcement learning tree long short-term memory） model based on enhanced deep learning is proposed. The selector and classifier are trained together to optimize the selection and classification process, which can effectively reduce the noise caused by remote supervision. The experimental results show that the proposed model in this paper can effectively extract entities and their relationships.

Key words: knowledge base construction, neural networks, reinforcement learning, entity extraction, entity relation extraction

王勇, 江洋, 王红滨, 侯莎. 面向科技情报分析的知识库构建方法[J]. 计算机工程与应用, 2022, 58(22): 142-149.

WANG Yong, JIANG Yang, WANG Hongbin, HOU Sha. Knowledge Base Construction Method for Scientific and Technical Information Analysis[J]. Computer Engineering and Applications, 2022, 58(22): 142-149.

参考文献

[1] 郭喜跃，何婷婷.信息抽取研究综述[J].计算机科学，2015，42（2）：14-17.
GUO X Y，HE T T.Survey about research on information extraction[J].Computer Science，2015，42（2）：14-17.
[2] 徐洁磐.知识库系统导论[M].北京：科学出版社，2000：62-73.
XU J P.Introduction to knowledge base system[M].Beijing：Science Press，2000：62-73.
[3] LEE D T，TSANG C P.Finding relevant knowledge in a knowledge base of linear logic[J].Knowledge-Based Systems，1998，10（6）：359-361.
[4] MAISTO A，MARTORELLI G，PAONE A，et al.Semi-automatic knowledge base expansion for question answering[C]//Proceedings of the 12th International Conference on Intelligent Networking and Collaborative Systems，2020：173-182.
[5] PAPPU A，BLANCO R，MEHDAD Y，et al.Lightweight multi-
lingual entity extraction and linking[C]//Proceedings of the 10th ACM International Conference on Web Search and Data Mining，2017：365-374.
[6] BARTOLI A，LORENZO A D，MEDVET E，et al.Active learning of regular expressions for entity extraction[J].IEEE Transactions on Cybernetics，2018，48（3）：1067-1080.
[7] YADAV S，EKBAL A，SAHA S，et al.Entity extraction in biomedical corpora：an approach to evaluate word embedding features with PSO based feature selection[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics，2017：1159-1170.
[8] 冯蕴天，张宏军，郝文宁，等.基于深度信念网络的命名实体识别[J].计算机科学，2016，43（4）：224-230.
FENG Y T，ZHANG H J，HAO W N，et al.Named entity recognition based deep belief net[J].Computer Science，2016，43（4）：224-230.
[9] DEWI I N，DONG S，HU J.Drug-drug interaction relation extraction with deep convolutional neural networks[C]//Proceedings of the 2017 IEEE International Conference on Bioinformatics and Biomedicine，2017：1795-1802.
[10] MIWA M，BANSAL M.End-to-end relation extraction using LSTMs on sequences and tree structures[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics，2016：1105-1116.
[11] XU K，REDDY S，FENG Y，et al.Question answering on freebase via relation extraction and textual evidence[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics，2016：2326-2336.
[12] GUPTA P，SCHüTZE H，ANDRASSY B.Table filling multi-task recurrent neural network for joint entity and relation extraction[C]//Proceedings of the 26th International Conference on Computational Linguistics，2016：81-106.
[13] 李灿，田秀霞，赵波.BiLSTM_DPCNN模型在电力客服工单数据分类中的应用[J].计算机系统应用，2021，30（2）：243-249.
LI C，TIAN X X，ZHAO B.Application of BiLSTM_DPCNN model in work order data classification for power customer service[J].Computer Systems & Applications，2021，30（2）：243-249.
[14] 张楚婷，常亮，王文凯，等.基于BiLSTM-CRF的细粒度知识图谱问答[J].计算机工程，2020，46（2）：41-47.
ZHANG C T，CHANG L，WANG W K，et al.Fine-grained question answering over knowledge graph based on BiLSTM-CRF[J].Computer Engineering，2020，46（2）：41-47.
[15] 吴思贤，何勇军，李辰阳，等.基于BiLSTM的智能语音餐厅推荐方法[J].物联网技术，2021，11（2）：27-31.
WU S X，HE Y J，LI C Y，et al.Intelligent voice restaurant recommendation method based on BiLSTM[J].Internet of Things Technologies，2021，11（2）：27-31.