Under a Creative Commons license open access Referred to by Journal of Safety Science and Resilience, Volume 2, Issue 3, September 2021, Pages 179 View PDF Highlights • A Two-Step-Matching method is designed to identify the precise target of Chinese entity from ambiguous user comments of public opinions. • BiLSTM-CRF model is used to extract potential entity and TF-IDF model is used to extract characteristic words from user comments. • Jaro–Winkler distance algorithm is used in the first matching process, where a business directory is built according to entity registration details. • In the second matching process, an industry-characteristic dictionary is introduced to identify precise target entity if ambiguity exists. • Associated rate and accuracy rate are used to evaluate the effect of the method. His current research interests include: Media big data modeling and analysis, knowledge management, and financial management. ☆ This work is partially supported by the National Natural Science Foundation of China (Grant Nos. 71901144 , 71771152 , 61773248 ), the Major Program of National Fund of Philosophy and Social Science of China (18ZDA088,20ZDA060 ), Shanghai Planning Office of Philosophy and Social Science Foundation (Grant No. 2019EXW001 ), Foundation of University of Finance and Economics (Grant No. 2017110709), and S-Tech internet communication project (Grant Nos. 2018PHD005 and 2018TECH003). © 2022 China Science Publishing & Media Ltd.

Author affiliations 1 Computer Science Department, Faculty of Computing and Media, Bina Nusantara University, Jakarta, Indonesia 11480 Buy this article in print 1755-1315/426/1/012168 Abstract Chatbots are having a spotlight in the current market. The reasoning behind this would be mobile applications are becoming a saturated market and messenger applications are surpassing social networking applications regarding to the number of active users.

In: IEEE international conference on acoustics, speech and signal processing ICASSP 2009 (pp. 3957–3960). Can, D., & Saraclar, M. (2011). Lattice indexing for spoken term detection. In: IEEE international conference on, acoustics, speech and signal processing, ICASSP 2009 (pp. 4885–4888). Rajabzadeh, M., Tabibian, S., Akbari, A., & Nasersharif, B. (2012a). An improved phone lattice search method for triphone based keyword spotting in online persian telephony speech.

Our contribution is a context sensitive string similarity measure which shows top level outcomes on datasets composed of concepts having the most synonyms derived (a) exclusively from SNOMED, and (b) from multiple UMLS sources (Table 1 ). Table 1: Characteristics of datasets # Dataset # of Concepts # of Terms 1 SNOMED most frequent concepts 155 5,000 2 UMLS most frequent concepts from multiple sources 100 4,979 SPED overcomes the main problem of existing edit distance algorithms, where match decisions are made independently for each character pair. As shown in Figure 1 , two strings s and t of lengths n and m are aligned and divided into substrings of the same length l. l is an adjustable parameter, representing a grid node size as described in step 2. (The word “grid” is used informally, as “arrangement.”) The last substring of either string may be longer than l , in cases when the length of a string is not a multiple of the node size l . The example depicted on Fig. 1 is built using two SNOMED terms: Back pain , CUI C0004604, and Bacterial infection , CUI C0004623.

One of the main challenges of building question answering systems is determining which relations within a knowledge graph match the keywords found in the Natural Language question. In order to bridge the gap between the simple yet ambiguous natural language question, and the difficult relation mapping problem, we propose ReMLOFT, an interactive relation mapping approach which relies on external evidence from a large corpus of text for mapping relations to the keywords found in a Natural Language question.

In: Proceedings of the 19th international conference on information and knowledge management, Toronto, ON, Canada, 26–30 October 2010. pp. 659–668. New York: ACM. [4]. Javed F, Hoang P, Mahoney T, et al. In: Proceedings of the international conference on information and communication technologies: from theory to applications, Damascus, Syria, 19–23 April 2004. [13]. Bizer C, Heese R, Mochol M, et al. (2005) The impact of semantic web technologies on job recruitment processes.

Because of its importance, many researchers are conducting studies to analyze trends that are the most discussed, to monitor earthquakes [8 ,9 ] or to collect political opinions [10 –12 ]. They are also working on collecting information about people's health by analyzing tweets (a tweet is a sentence on Twitter) [13 –16 ]. Although these tweets are limited to 280 characters in USA and 140 characters in Korea, Japan, and China since 2017, it is difficult to extract information related to disease [17 –22 ] because they have various attributes such as irregular grammar, repetition of meaningless text, and lots of advertising spam [3 ]. Many researchers have developed and run disease surveillance systems to solve these problems. The components required for their algorithms are shown in Table 1 . The ranking algorithm of CCA is defined as: (1) We examine how accurate CCA is to extract disease-related topics from news and SNS compared to other algorithms by captured disease-related incidents in Section 5.

Authors: Umutcan Şimşek 1 , Kevin Angele 2 , Elwin Huaman 3 , Elias Kärle 4 , Oleksandra Panasiuk 5 , Ioan Toma 6 , Jürgen Umbrich 7 , … Alexander Wahler 8 Dieter Fensel Semantic Technology Institute Innsbruck, Department of Computer Science, University of Innsbruck, Innsbruck, Austria Umutcan Şimşek Semantic Technology Institute Innsbruck, Department of Computer Science, University of Innsbruck, Innsbruck, Austria Kevin Angele Semantic Technology Institute Innsbruck, Department of Computer Science, University of Innsbruck, Innsbruck, Tirol, Austria, Onlim GmbH, Telfs, Austria Elwin Huaman Semantic Technology Institute Innsbruck, Department of Computer Science, University of Innsbruck, Innsbruck, Austria Elias Kärle Semantic Technology Institute Innsbruck, Department of Computer Science, University of Innsbruck, Innsbruck, Austria Oleksandra Panasiuk Semantic Technology Institute Innsbruck, Department of Computer Science, University of Innsbruck, Innsbruck, Austria Ioan Toma Onlim GmbH, Telfs, Austria Jürgen Umbrich Onlim GmbH, Telfs, Austria Alexander Wahler Onlim GmbH, Telfs, Austria Describes methods and tools that empower information providers to build and maintain knowledge graphs Covers the entire lifecycle, from knowledge graph construction and implementation to validation, error correction and further enrichments Illustrates practical usage through several pilot implementations in various domains 20k Accesses 82 Citations 8 Altmetric Sections Table of contents About this book Keywords Authors and Affiliations About the authors Bibliographic Information Table of contents (5 chapters) Conclusions Dieter Fensel, Umutcan Şimşek, Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Panasiuk et al. The book has been co-authored under his guidance, by his team of researchers at STI Innsbruck (Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Panasiuk and Umutcan Şimşek) and Onlim GmbH (Alexander Wahler, Jürgen Umbrich and Ioan Toma). Bibliographic Information Book Title : Knowledge Graphs Book Subtitle : Methodology, Tools and Selected Use Cases Authors : Dieter Fensel, Umutcan Şimşek, Kevin Angele, Elwin Huaman, Elias Kärle, Oleksandra Panasiuk, Ioan Toma, Jürgen Umbrich, … Alexander Wahler DOI : https://doi.org/10.1007/978-3-030-37439-6 Publisher : Springer Cham eBook Packages : Computer Science , Computer Science (R0) Copyright Information : Springer Nature Switzerland AG 2020 Softcover ISBN : 978-3-030-37438-9 Published: 01 February 2020 eBook ISBN : 978-3-030-37439-6 Published: 31 January 2020 Edition Number : 1 Number of Pages : XVI, 148 Number of Illustrations : 8 b/w illustrations, 8 illustrations in colour Topics : Knowledge Based Systems , Computer and Information Systems Applications , Computer Application in Administrative Data Processing