基于Tri-BiLSTM-CNN的钻井安全问答系统

doi:10.11885/j.issn.1674-5086.2020.05.12.06

西南石油大学学报(自然科学版) ›› 2020, Vol. 42 ›› Issue (6): 157-164.DOI: 10.11885/j.issn.1674-5086.2020.05.12.06

• 油气田人工智能技术与应用专刊 • 上一篇下一篇

基于Tri-BiLSTM-CNN的钻井安全问答系统

王兵¹, 郑亚梅¹, 陈茂柯², 高凌云²

1. 西南石油大学计算机科学学院, 四川成都 610500;
2. 中国石油集团测井有限公司西南分公司, 重庆渝北 401120

收稿日期:2020-05-12 发布日期:2020-12-21
通讯作者: 王兵,E-mail:w9521423@sina.com
作者简介:王兵,1977年生,男,汉族,四川南充人,副教授,主要从事钻井安全评价、数据分析与挖掘等方面的研究。E-mail:w9521423@sina.com;郑亚梅,1994年生,女,汉族,四川眉山人,硕士研究生,主要从事深度学习与自然语言处理方面的研究。E-mail:1005094519@qq.com;陈茂柯,1974年生,男,汉族,四川隆昌人,主要从事测井安全生产管理方面的研究。E-mail:8892271@qq.com;高凌云,1984年生,男,汉族,四川泸州人,主要从事井场信息化及钻井仪器仪表的研究。E-mail:403815459@qq.com
基金资助:
国家科技重大专项（2016ZX05020-006）

Question Answering System for Drilling Safety Based on Tri-BiLSTM-CNN

WANG Bing¹, ZHENG Yamei¹, CHEN Maoke², GAO Lingyun²

1. School of Computer Science, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
2. Southwest Branch of China Petroleum Logging Co. Ltd., Yubei, Chongqing 401120, China

Received:2020-05-12 Published:2020-12-21

摘要/Abstract

摘要： 特定领域的FAQ问答系统通常存在以下3个问题：（1）如何有效地对句子进行语义表示；（2）如何有效地进行句子间的语义匹配；（3）领域词汇的分词问题。为解决上述3个问题，提出一种基于Tri-BiLSTM-CNN的深度学习模型。首先，将双向长短期记忆网络和卷积神经网络结合构建网络模型，综合利用了BiLSTM处理序列化数据的优势和CNN捕获局部特征的优势。然后，采用Triplet并列式排列结构进行句子之间的匹配。最后，使用字向量替代词向量，避免了分词错误对模型的影响。在钻井安全领域的真实数据集上进行实验验证，结果表明，Tri-BiLSTM-CNN模型能更好地对句子语义进行向量化表征，显著提升句子相似度计算的准确率，而且效果明显优于CNN和LSTM两种网络结构。将该模型用于钻井安全领域的FAQ问答系统中，有效减少了人工成本，对改善钻井工作的效率和质量具有重要意义和应用价值。

关键词: 钻井安全, 问答系统, 双向长短期记忆网络, 卷积神经网络, 句子相似度计算

Abstract: The FAQ question answering system in a specific field usually has the following three problems:(1) how to effectively represent sentences semantically; (2) how to effectively match sentences semantically; (3) how to segment domain words. To solve the above three problems, a deep learning model based on Triplet BiLSTM-CNN is proposed. Firstly, the bidirectional long-term memory network and convolutional neural network are combined to construct the network model, which makes full use of the advantages of BiSLTM in processing the serialized data and the advantages of CNN in capturing local features. Then, the Triplet parallel structure is used to match sentences. Finally, character vector is used instead of word vector to avoid the influence of segmentation error on the model. The experimental results on real data sets in the field of drilling safety show that Triplet BiLSTM-CNN model can better vectorize sentence semantics and significantly improve the accuracy of sentence similarity calculation, and the effect is significantly better than that of CNN and LSTM. The model is applied to the FAQ question answering system in the field of drilling safety, which can effectively reduce the labor cost, and is of great significance and application value to improve the efficiency and quality of drilling work.

Key words: drilling safety, question answering system, bidirectional long short term memory, convolution neural network, question similarity computation

中图分类号:

TE319

王兵, 郑亚梅, 陈茂柯, 高凌云. 基于Tri-BiLSTM-CNN的钻井安全问答系统[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 157-164.

WANG Bing, ZHENG Yamei, CHEN Maoke, GAO Lingyun. Question Answering System for Drilling Safety Based on Tri-BiLSTM-CNN[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2020, 42(6): 157-164.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal15.magtechjournal.com/Jwk_xnzk/CN/10.11885/j.issn.1674-5086.2020.05.12.06

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2020/V42/I6/157

参考文献

[1] 郭天翼,彭敏,伊穆兰,等. 自然语言处理领域中的自动问答研究进展[J]. 武汉大学学报(理学版),2019,65(5):417-426. doi:10.14188/j.1671-8836.2019.05.001 GUO Tianyi, PENG Min, YI Mulan, et al. Advances in question answering in natural language processing[J]. Journal of Wuhan University (Natural Science Edition), 2019, 65(5):417-426. doi:10.14188/j.1671-8836.2019.05.001
[2] WADHWA S, CHANDU K R, NYBERG E. Comparative analysis of neural QA models on SQuAD[C]. arXiv:W18-2610, 2018. doi:10.18653/v1/W18-2610
[3] SU D, XU Y, WINATA G I, et al. Generalizing question answering system with pretrained language model finetuning[C]. Proceedings of the 2nd Workshop on Machine Reading for Question Answering, 2019. doi:10.18653/v1/D19-5827
[4] 曹建文,万福成. 面向自动问答系统的问句相似度计算研究[J]. 重庆大学学报, 2019, 42(9):115-123. doi:10.11835/j.issn.1000-582X.2019.09.013 CAO Jianwen, WAN Fucheng. Question similarity computing method for automatic question answering system[J]. Journal of Chongqing University, 2019, 42(9):115-123. doi:10.11835/j.issn.1000-582X.2019.09.013
[5] WAN S, DRAS M, DALE R, et al. Using dependencybased features to take the ‘para-farce’ out of paraphrase[C]. Proceedings of the Australasian Language Technology Workshop, 2006:131-138.
[6] DAS D, SMITH N A. Paraphrase identification as probabilistic quasi-synchronous recognition[C]. Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP, 2009:468-476. doi:10.3115/1687878.1687944
[7] FERNANDO S, STEVENSON M. A semantic similarity approach to paraphrase detection[C]. Proceedings of the 11th Annual Research Colloquium of the UK Special Interest Group for Computational Linguistics, 2008:45-52.
[8] GUO W, DIAB M. Modeling sentences in the latent space[C]. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics:Long Papersvolume, 2012:864-872.
[9] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521:436-444. doi:10.1038/nature14539
[10] 冯兴杰,张乐,曾云泽. 基于多注意力CNN的问题相似度计算模型[J]. 计算机工程, 2009, 45(9):284-290. doi:10.1967-8/j.issn.1000-3428.0052098 FENG Xingjie, ZHANG Le, ZENG Yunze. Question similarity calculation model based on multi-attention CNN[J]. Computer Engineering, 2009, 45(9):284-290. doi:10.19678/j.issn.1000-3428.0052098
[11] 黄江平,姬东鸿. 基于卷积网络的句子语义相似性模型[J]. 华南理工大学学报(自然科学版), 2017, 45(3):68-75. doi:10.3969/j.issn.1000-565X.20-17.03.010 HUANG Jiangping, JI Donghong. Convolutional net-work-based semantic similarity model of sentences[J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(3):68-75. doi:10.3969/j.issn.1000-565X.20-17.03.010
[12] KALCHBRENNER N, GREFENSTETTE E, BLUNSOM P. A convolutional neural network for modelling sentences[C]. arXiv:P14-1062, 2014. doi:10.3115/v1/P14-1062
[13] YIN W, SCHÜTZE H. Convolutional neural network for paraphrase identification[C]. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, 2015:901-911.
[14] SOCHER R, HUANG E H, PENNIN J, et al. Dynamic pooling and unfolding recursive autoencoders for paraphrase detection[C]. Advances in Neural Information Processing Systems, 2011:801-809.
[15] HU B, LU Z, LI H, et al. Convolutional neural network architectures for matching natural language sentences[C]. Advances in Neural Information Processing Systems, 2014:2042-2050.
[16] MUELLER J, THYAGARAJAN A. Siamese recurrent architectures for learning sentence similarity[C]. Thirtieth AAAI Conference on Artificial Intelligence, 2016.
[17] NECULOIU P, VERSTEEGH M, ROTARU M. Learning text similarity with siamese recurrent networks[C]. Proceedings of the 1st Workshop on Representation Learning for NLP, 2016:148-157.
[18] 徐雄. 基于深度学习的问答系统研究[J]. 湖北师范大学学报(自然科学版),2019,39(1):10-18. doi:10.3969/j.issn.2096-3149.2019.01.003 XU Xiong. Research on question answering system based on deep learning[J]. Journal of Hubei Normal University (Natural Science), 2019, 39(1):10-18. doi:10.3969/j.issn.2096-3149.2019.01.003
[19] 夏元昉. 基于深度学习的问答系统技术研究[D]. 杭州:浙江大学, 2017. XIA Yuanfang. Research on question answering system based on deep learning[D]. Hangzhou:Zhejiang University, 2017.
[20] 陈瑛,陈昂轩,董玉博,等. 基于LSTM的食品安全自动问答系统方法研究[J]. 农业机械学报, 2019, 50(S1):380-384. doi:10.6041/j.issn.1000-1298.2019.S0.058 CHEN Ying, CHEN Angxuan, DONG Yubo, et al. Methods of food safety question answering system based on LSTM[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(S1):380-384. doi:10.6041/j.issn.1000-1298.2019.S0.058
[21] 刘依红,杨波,孙宇宁,等. 基于BiLSTM的婚姻法自然语言问答[J]. 计算机工程与设计, 2019, 40(4):1190-1195. doi:10.16208/j.issn.1000-7024.2019.04.046 LIU Yihong, YANG Bo, SUN Yuling, et al. Q & A of natural language in marriage law based on BiLSTM[J]. Computer Engineering and Design, 2019, 40(4):1190-1195. doi:10.16208/j.issn1000-7024.2019.04.046
[22] HOFFER E, AILON N. Deep metric learning using triplet network[C]. International Workshop on Similarity-Based Pattern Recognition, Springer, Cham, 2015:84-92.
[23] JÜRGEN S. Deep learning in neural networks:An overview[J]. Neural Networks, 2015, 61:85-117. doi:10.1016/j.neunet.2014.09.003
[24] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. doi:10.1162/neco.1997.9.8.1735
[25] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[J]. Advances in Neural Information Processing Systems, 2013, 26:3111-3119.

基于Tri-BiLSTM-CNN的钻井安全问答系统

Question Answering System for Drilling Safety Based on Tri-BiLSTM-CNN

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	黄旭日, 代月, 徐云贵, 唐静. 基于深度学习算法不同数据集的地震反演实验[J]. 西南石油大学学报(自然科学版), 2020, 42(6): 16-25.
[2]	祝效华, 谌柯宇, 毛宇, 刘骉. 水平井段脉冲携岩数值模拟研究[J]. 西南石油大学学报(自然科学版), 2016, 38(6): 164-171.