A deep learning methodology for automatic extraction and discovery of technical intelligence

被引：16

作者：

Xu, Jianguo ^{[1
]}

Guo, Lixiang ^{[1
]}

Jiang, Jiang ^{[1
]}

Ge, Bingfeng ^{[1
]}

Li, Mengjun ^{[1
]}

机构：

[1] Natl Univ Def Technol, Coll Syst Engn, Changsha 410073, Hunan, Peoples R China

来源：

TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE | 2019年 / 146卷

基金：

中国国家自然科学基金;

关键词：

Technical intelligence; CRF-BiLSTM; Deep learning; Intelligence monitoring; EMERGING TECHNOLOGIES; NETWORK; KNOWLEDGE; MACHINE; TEXT;

D O I：

10.1016/j.techfore.2019.06.004

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

It is imperative and arduous to acquire product and business intelligence of global technical market. In this paper, a deep learning methodology is proposed to automatically extract and discover vital technical information from large-scale news dataset. More specifically, six kinds of technical elements are first defined to provide the concrete syntax information. Next, the CRF-BiLSTM approach is used to automatically extract technical entities, in which a conditional random field (CRF) layer is added on top of bidirectional long short-term memory (BiLSTM) layer. Then, three indicators including timeliness, influence and innovativeness are designed to evaluate the value of intelligence comprehensively. Finally, as a case study, technical news on three military-related websites is utilized to illustrate the efficiency and effectiveness of the foregoing methodology with the result of 80.82 (F-score) in comparison to four other models. In more detail, data on unmanned systems are extracted to summarize the state-of-the-art, and track up-to-the-minute innovations and developments in this field.

引用

页码：339 / 351

页数：13

共 35 条

[1] Innovation network [J].

Acemoglu, Daron ;

Akcigit, Ufuk ;

Kerr, William R. .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (41) :11483-11488

[2] Data-driven predictions in the science of science [J].

Clauset, Aaron ;

Larremore, Daniel B. ;

Sinatra, Roberta .

SCIENCE, 2017, 355 (6324) :477-480

[3] Analysis of named entity recognition and linking for tweets [J].

Derczynski, Leon ;

Maynard, Diana ;

Rizzo, Giuseppe ;

van Erp, Marieke ;

Gorrell, Genevieve ;

Troncy, Raphael ;

Petrak, Johann ;

Bontcheva, Kalina .

INFORMATION PROCESSING & MANAGEMENT, 2015, 51 (02) :32-49

[4] Automatic extraction of function-behaviour-state information from patents [J].

Fantoni, G. ;

Apreda, R. ;

Dell'Orletta, F. ;

Monge, M. .

ADVANCED ENGINEERING INFORMATICS, 2013, 27 (03) :317-334

[5] Science of science [J].

Fortunato, Santo ;

Bergstrom, Carl T. ;

Boerner, Katy ;

Evans, James A. ;

Helbing, Dirk ;

Milojevic, Stasa ;

Petersen, Alexander M. ;

Radicchi, Filippo ;

Sinatra, Roberta ;

Uzzi, Brian ;

Vespignani, Alessandro ;

Waltman, Ludo ;

Wang, Dashun ;

Barabasi, Albert-Laszlo .

SCIENCE, 2018, 359 (6379)

[6] Identifying the evolutionary process of emerging technologies: A chronological network analysis of World Wide Web conference sessions [J].

Furukawa, Takao ;

Mori, Kaoru ;

Arino, Kazuma ;

Hayashi, Kazuhiro ;

Shirakawa, Nobuyuki .

TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE, 2015, 91 :280-294

[7] Funding Data from Publication Acknowledgments: Coverage, Uses, and Limitations [J].

Grassano, Nicola ;

Rotolo, Daniele ;

Hutton, Joshua ;

Lang, Frederique ;

Hopkins, Michael M. .

JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY, 2017, 68 (04) :999-1017

[8] Character-level neural network for biomedical named entity recognition [J].

Gridach, Mourad .

JOURNAL OF BIOMEDICAL INFORMATICS, 2017, 70 :85-91

[9] Deep learning with word embeddings improves biomedical named entity recognition [J].

Habibi, Maryam ;

Weber, Leon ;

Neves, Mariana ;

Wiegandt, David Luis ;

Leser, Ulf .

BIOINFORMATICS, 2017, 33 (14) :I37-I48

[10] Literature Based Discovery: Models, methods, and trends [J].

Henry, Sam ;

McInnes, Bridget T. .

JOURNAL OF BIOMEDICAL INFORMATICS, 2017, 74 :20-32

← 1 2 3 4 →