Information Extraction Based on Multi-turn Question Answering for Analyzing Korean Research Trends

Analyzing Research and Development(R&D)trends is important because it can influence future decisions regarding R&D direction.In typical trend analysis,topic or technology taxonomies are employed to compute the popularities of the topics or codes over time.Although it is simple and effective,the taxonomies are difficult to manage because new technologies are introduced rapidly.Therefore,recent studies exploit deep learning to extract pre-defined targets such as problems and solutions.Based on the recent advances in question answering(QA)using deep learning,we adopt a multi-turn QA model to extract problems and solutions from Korean R&D reports.With the previous research,we use the reports directly and analyze the difficulties in handling them using QA style on Information Extraction(IE)for sentence-level benchmark dataset.After investigating the characteristics of Korean R&D,we propose a model to deal with multiple and repeated appearances of targets in the reports.Accordingly,we propose a model that includes an algorithm with two novel modules and a prompt.A newly proposed methodology focuses on reformulating a question without a static template or pre-defined knowledge.We show the effectiveness of the proposed model using a Korean R&D report dataset that we constructed and presented an in-depth analysis of the benefits of the multi-turn QA model.

Research on Extraction Method of Surface Information Based on Multi-Feature Combination Such as Fractal Texture

Because of the developed economy and lush vegetation in southern China, the following obstacles or difficulties exist in remote sensing land surface classification: 1) Diverse surface composition types;2) Undulating terrains;3) Small fragmented land;4) Indistinguishable shadows of surface objects. It is our top priority to clarify how to use the concept of big data (Data mining technology) and various new technologies and methods to make complex surface remote sensing information extraction technology develop in the direction of automation, refinement and intelligence. In order to achieve the above research objectives, the paper takes the Gaofen-2 satellite data produced in China as the data source, and takes the complex surface remote sensing information extraction technology as the research object, and intelligently analyzes the remote sensing information of complex surface on the basis of completing the data collection and preprocessing. The specific extraction methods are as follows: 1) extraction research on fractal texture features of Brownian motion;2) extraction research on color features;3) extraction research on vegetation index;4) research on vectors and corresponding classification. In this paper, fractal texture features, color features, vegetation features and spectral features of remote sensing images are combined to form a combination feature vector, which improves the dimension of features, and the feature vector improves the difference of remote sensing features, and it is more conducive to the classification of remote sensing features, and thus it improves the classification accuracy of remote sensing images. It is suitable for remote sensing information extraction of complex surface in southern China. This method can be extended to complex surface area in the future.

A Joint Entity Relation Extraction Model Based on Relation Semantic Template Automatically Constructed

The joint entity relation extraction model which integrates the semantic information of relation is favored by relevant researchers because of its effectiveness in solving the overlapping of entities,and the method of defining the semantic template of relation manually is particularly prominent in the extraction effect because it can obtain the deep semantic information of relation.However,this method has some problems,such as relying on expert experience and poor portability.Inspired by the rule-based entity relation extraction method,this paper proposes a joint entity relation extraction model based on a relation semantic template automatically constructed,which is abbreviated as RSTAC.This model refines the extraction rules of relation semantic templates from relation corpus through dependency parsing and realizes the automatic construction of relation semantic templates.Based on the relation semantic template,the process of relation classification and triplet extraction is constrained,and finally,the entity relation triplet is obtained.The experimental results on the three major Chinese datasets of DuIE,SanWen,and FinRE showthat the RSTAC model successfully obtains rich deep semantics of relation,improves the extraction effect of entity relation triples,and the F1 scores are increased by an average of 0.96% compared with classical joint extraction models such as CasRel,TPLinker,and RFBFN.

Research on Technology Development of Traditional Chinese Medicine Extraction Based on Patent Information

Objective To understand the development status of traditional Chinese medicine extraction technology,so as to provide a reference for enterprises and scientific research institutions to determine the direction of technological innovation.Besides,the government can formulate scientific and technological innovation strategies.Methods Based on patent information,statistical methods were applied to analyze the development of traditional Chinese medicine extraction technology.Then,the core technology was identified by constructing a patent citation network.Finally,the main path analysis method was applied to discover the technological evolution path.Results and Conclusion The extraction technology of traditional Chinese medicine is still in the growth stage.At present,its R&D is based on enterprises,supplemented by scientific research institutions.The core technologies are ultrasonic extraction and enzymatic extraction.The main path represented by enzymatic extraction technology reveals the evolution process of traditional Chinese medicine extraction technology.Based on this,relevant suggestions are put forward.Firstly,technological innovation cooperation should be strengthened to explore new models of achievement transformation and cooperation.Secondly,key enterprises of technology clusters should be cultivated to accelerate breakthroughs in core technologies.Thirdly,combined technologies can achieve high-efficiency enzyme-assisted extraction and open up new ways of extracting traditional Chinese medicine.Fourthly,traditional techniques should be improved to develop innovative modern techniques.

Landfill Site Suitability Assessment Using Geographic Information System (GIS) and Analytic Hierarchy Process (AHP) in Butuan City, Philippines

Landfilling is one of the most effective and responsible ways to dispose of municipal solid waste(MSW).Identifying landfill sites,however,is a challenging and complex undertaking because it depends on social,environmental,technical,economic,and legal issues.This study aims to map the optimal sites that were environmentally suitable for locating a landfill site in Butuan City,Philippines.With reference to the policy requirements from DENR Section I,Landfill Site Identification Criteria and Screening Guidelines of National Solid Waste Management Commission,the integration of a Geographic Information System(GIS)model builder and Analytical Hierarchy Process(AHP)has been used in this study to address the aforementioned challenges related to the landfill site suitability analysis.Based on the generated sanitary landfill suitability map,results showed that Barangay Tungao(1131.42967 ha)and Florida(518.48 ha)were able to meet and consider the three(3)main components,namely economic,environmental,and physical criteria,and are highly suit­able as landfill site locations in Butuan City.It is recommended that there will conduct a geotechnical evaluation,involv­ing rigorous geological and hydrogeological assessment employing a combination of site investigation and laboratory techniques.In addition,additional specific social,ecological,climatic,and economic factors need to be considered(i.e.including impact on humans,flora,fauna,soil,water,air,climate,and landscape).

Locating Global System for Mobile Communication(GSM)Base Stations Using Geographic Information System(GIS)

The global system for mobile communication(GSM)is planned to meet the needs of the whole subscribers.The number of subscribers increased as the population increased due to the acceptance of GSM services by the subscribers.Thus,there should be a way to monitor base stations that will meet the increasing demand of subscribers in any area as a population surge will lead to more subscriptions.This will allow GSM network operators to serve their subscribers better and ease network congestion.This work presents a review of mobile evolution from the first generation to the fifth generation.A review of global positioning system(GPS)technology and its applications to geographic information systems(GIS)was done.The coordinates of these base stations were taken using a GPS device.These base station coordinates were then exported to QGIS for the design of the map.Thereafter,the output map was then integrated into the website.The discussions on the results followed and some useful suggestions given will go a long way to help the operators of GSM in Nigeria and in general.If the propositions given are adhered to,it will go a long way to help the operators reduce congestion on their network and thereby increase the satisfaction of the subscribers.

Basic theory and key technologies for marine geographic information system

Marine geographic information system （MGIS） has great ability to deal with the spatio-temporal problems and has potential superiority when it is applied to oceanography. Using the feature extraction of oceanic phenomena as a case study, the functions of the MGIS are analyzed, and thus the position of MGIS in the oceanography is defined. Comparing the requirement of MGIS with that of the traditional GIS which has been developed in the terrestrial applications in the past four decades, the frame for the functions of MGIS is constructed. According to the established MGIS, some key technologies are discussed in detail with emphasis on the specialities which can distinguish the MGIS from the traditional GIS.

Geographical Information System-Based Assessment of Ecological Security in Changbai Mountain Region

Ecological security defined as the creation of a condition where the physical surroundings of a community provide for the needs of its inhabitants without diminishing its natural stock,which is important for regional security and social stability.In recent years,land use patterns in the Changbai Mountain region have changed significantly with intensive human activities,and consequently led to increasing problems in regional ecological security.Based on the Pressure-State-Impact-Response(PSIR) model and the mathematical method of catastrophe progression supported by geographical information system(GIS),the ecological security situation of the study area under land use and cover change(LUCC) was evaluated.The results indicated that the ecological security in Changbai Mountain region varied nonlinearly,which got better from 1990 to 2000 but became worse from 2000 to 2007,the ecological security levels in Changbai Mountain region were mainly medium and medium to low during the past 17 years,with higher values of Ecological Security Index(ESI) in the central region and lower values in the east and west,the ecological security situation was more serious in the settlements and river valleys,where the LUCC was most remarkable.

Hazards Assessment of Regional Debris Flows Based on Geographic Information Science

Supported by the spatial analysis feature of geographic information science and assessment model of regional debris flows, hazards degrees of the debris flows in the Upper Yangtze River Watershed （UYRW） are divided into five grades based on grid cell. The area of no danger, light danger, medium danger, severe danger and extreme severe danger regions respectively are 278 000, 288 000, 217 000, 127 000, 15 000 km^2. Furthermore, the counties in the UYRW are classified into four classes based on the hazards degrees in each county. The number of severe danger, medium danger, light danger and no danger counties respectively are 49, 82, 77 and 105. The assessment results will be provided for the hazards forecasting and mitigation in the UYRW and ongoing regionalization of Main Function Regions in China as data and technique framework.

Spatial variations of aluminum species in drinking water supplies in Xi'an studied applying geographic information system

This article aimed to investigate the variation of aluminum species and the effects of coagulant type and water quality on aluminum speciation in drinking water. Statistical analysis showed that the concentration of total aluminum （AlT） of drinking water in Xi＇ an ranged from 0.051 to 0.417 mg/L and the concentration of A1T in about 24.7% studied samples was higher than the currently recommended value （0.2 mg/L）. The areas fed by surface water plants had a larger portion （39.4%） of samples over the recommended value. In drinking water treated by alum coagulant, the average concentration of monomeric aluminum （Ala） was higher than that in water treated by poly aluminum chlorine （PACl） and poly aluminum ferric chloride （PAFC）. The average concentrations of polynuclear aluminum （Alb） and colloidal/suspended aluminum （Ale） in the drinking water treated by alum were lower than those in water treated by PACl and PAFC. There was a notable decrease in AlT along with the delivery pipeline away from the plants, with an average decline of about 36 μg/（L-km）. Besides coagulant type, water quality also could affect aluminum speciation. In drinking water without orthophosphate, the concentrations of Ala and AlT were positively correlated with pH; while, in drinking water with orthophospbate, the concentrations of Ala and AlT were negatively correlated with pH. The addition of orthophosphate salts in the drinking water treatment process would be an effective method for aluminum control in pH range 6.5-8.2.

Research on Development of Agricultural Geographic Information Ontology

This paper first analyzes the reason that agricultural geographic information gives rise to semantic heterogeneity and solution thereof. Although OWL （web ontology language） is the standard of ontology representation language in semantic web, it is insufficient in representing spatial characteristics, especially spatial relationship. Consequently it is pointed out to build geo-ontology by virtue of three theories such as mereology, location theory and topology in this paper. This paper introduces mereology, location theory and topology, and then discusses how to adopt these three theories to build geo-ontology. The outcome of experiment shows that solution put forward by this paper is feasible.

A Classification Method for Web Information Extraction

Web information extraction is viewed as a classification process and a competing classification method is presented to extract Web information directly through classification. Web fragments are represented with three general features and the similarities between fragments are then defined on the bases of these features. Through competitions of fragments for different slots in information templates, the method classifies fragments into slot classes and filters out noise information. Far less annotated samples are needed as compared with rule-based methods and therefore it has a strong portability. Experiments show that the method has good performance and is superior to DOM-based method in information extraction. Key words information extraction - competing classification - feature extraction - wrapper induction CLC number TP 311 Foundation item: Supported by the National Natural Science Foundation of China (60303024)Biography: LI Xiang-yang (1974-), male, Ph. D. Candidate, research direction: information extraction, natural language processing.

Chaining Distributed Geographic Information Web Services Based on Ontology

To solve the problem of chaining distributed geographic information Web services （GI Web services）, this paper provides an ontology-based method. With this method, semantic service description can be achieved by semantic annotation of the elements in a Web service description language（WSDL） document with concepts of geographic ontology, and then a common under-standing about service semantics between customers and providers of Web services is built. Based on the decomposition and formalization of customer requirements, the discovery, composition and execution of GI Web services are explained in detail, and then a chaining of GI Web services is built and used to achieve the customer＇s requirement. Finally, an example based on Web ontology language for service （OWL-S） is provided for testing the feasibility of this method.

Remote sensing and geographic information systems techniques in studies on treeline ecotone dynamics

We performed a meta-analysis on over 100 studies applying remote sensing(RS)and geographic information systems(GIS)to understand treeline dynamics.A literature search was performed in multiple online databases,including Web of Knowledge(Thomson Reuters),Scopus(Elsevier),BASE(Bielefeld Academic Search Engine),CAB Direct,and Google Scholar using treeline-related queries.We found that RS and GIS use has steadily increased in treeline studies since 2000.Spatialresolution RS and satellite imaging techniques varied from low-resolution MODIS,moderate-resolution Landsat,to high-resolution WorldView and aerial orthophotos.Most papers published in the 1990s used low to moderate resolution sensors such as Landsat Multispectral Scanner and Thematic Mapper,or SPOT PAN(Panchromatic)and MX(Multispectral)RS images.Subsequently,we observed a rise in high-resolution satellite sensors such as ALOS,GeoEye,IKONOS,and WorldView for mapping current and potential treelines.Furthermore,we noticed a shift in emphasis of treeline studies over time:earlier reports focused on mapping treeline positions,whereas RS and GIS are now used to determine the factors that control treeline variation.

THE MANAGEMENT AND RESEARCH OF GEOGRAPHICAL NAMES USING GEOGRAPHICAL INFORMATION SYSTEM

Based on the combination of Geographical information system(GIS)with the research ofToponymy,some foundational problems of the Geographical Name Information System(GINS)are discussed in this paper.The present situation of Toponymical research is anal-ysed and the necessity of introducing the GIS tools to the research of Toponymy is demon-strated.The conceptual model of the GNIS and the structure of Geographical name Database(GND)are discussed.The basic functions of the GNIS software for management and re-search of geographical name are suggested.Some issues are stated such as the applicationand potential of the combination of GIS with CAD in the management and research of To-ponymy,the combination of GNIS with other spatial information system and sharing the in-formation with each other,the research and development of GNIS, etc.

The application of Yangtze Estuary Tidal Wetlands Geographic Information System

Yangtze Estuary Tidal Wetlands Geographic Information System (YETWGIS) is a comprehensive software system for environmental management and decision of Yangtze estuary tidal wetlands. Based on MapObjects components technology, Data Mining technology, mathematical modeling method and Visual Basic language, this software system has many functions such as displaying, editing, querying and searching, spatial statistics and analysis, thematic map compiling, and environmental quality evaluation. This paper firstly outlined the system structure, key techniques, and achieving methods of YETWGIS, and then, described the core modules (the thematic map compiling module and environmental quality evaluation model module) in detail. In addition, based on information entropy model, it thoroughly discussed the methods of environmental quality evaluation and indicators' weight calculation. Finally, by using YETWGIS, this paper analyzed the spatial distribution characteristics of Heavy Metal and Persistent Organic Pollutants (POPs) of the Yangtze estuary tidal wetlands in 2002, and evaluated the environmental quality of the Yangtze estuary tidal wetlands in 2003.

Application and research of global grid database design based on geographic information

Energy crisis and climate change have become two seriously concerned issues universally. As a feasible solution, Global Energy Interconnection(GEI) has been highly praised and positively responded by the international community once proposed by China. From strategic conception to implementation, GEI development has entered a new phase of joint action now. Gathering and building a global grid database is a prerequisite for conducting research on GEI. Based on the requirement of global grid data management and application, combining with big data and geographic information technology, this paper studies the global grid data acquisition and analysis process, sorts out and designs the global grid database structure supporting GEI research, and builds a global grid database system.

The application of geographic information technology to coastal geomorphology

With the development of modern oceanic observation technologies, coastal survey data have been experiencing a substantial growth. The integration management of the data from different disciplines, different sources and different formats has become a major research field in coastal geomorphology by using Geographic Information System （GIS）. This paper puts forward a new methodology framework of GIS techniques in coastal ocean geomorphology, including data acquisition, process, analysis, and representation. It focuses on some major GIS techniques to study the land-ocean interaction mechanism, such as spatial analysis, submarine topography model and three-dimension （3D） visualization, and apply its result to coastal urban planning, harbor site selection and geomorphology environment about coral reef and islands on the continental shelf. The case studies cover the whole coastal ocean to serve the social community, economical development and diplomatic rights for decision-making all round in the coastal zone. The research shows clearly that the application of coastal multi-source geospatial platform has changed the traditional coastal geomorphology science dramatically from its research scope, fields and methods, however, as made clear in this paper, extracting accurate information from remote sensing data and GIS databases for coastal geomorphological applications is a nontrivial challenge that requires the combined knowledge and skills of information scientists and geomorphologists.

Integration technology research on marine geographical information system

It is urgent and necessary to integrate a marine geographical information system （MGIS） with marine remote sensing detection modules. On the basis of the current technology and features of applications, an open three-layer integration framework is designed. At the data layer, a two-level three-base integration mechanism based on the plug-in technology is applied; At the function layer, an integration mode based on API, DLL, EXE and COM is discussed; and at the application layer, a sharing mechanism based on the clients/service is adopted. As an example, the remote sensing integrated application information system of China＇s coastal zone and offshore （MaXplorer1. 0） with muhiecology remote sensing fusion and assimilation module, surge detection module as well as eight other thematic application modules is integrated, and the key technology of integration is discussed at different layers and in different modules. The result shows that it is possible to realize the conformity of technology and resources and to provide the incorporate technology platform for marine information operational functioning after applying the integration framework.

Spatial and Dynamic Analysis of Regional Sustainable Development Using Geographic Information System and Relative Carrying Capacity of Resources

Relative carrying capacity of resources is an index to measure sustainable development through carrying capacity. Case studies of eleven cities in Zhejiang (Hangzhou, Ningbo, Wenzhou, Jiaxing, Huzhou, Shaoxing, Jinhua, Quzhou, Zhoushan, Taizhou and Lishui) illustrated regional sustainable development approach. In this study, to provide insight into spatial and dynamic analysis of region sustainable development, we calculated the relative carrying capacity of land resources and economical resources and synthetical carrying capacity of resources in different cities in Zhejiang, and geographic information system was carried out. The results showed that all cities but Hangzhou and Ningbo were ecologically sustainable, and relative carrying capacity of land resources in northern and eastern Zhejiang was larger than those in southern and western Zhejiang. The sampling years of Wenzhou, Hangzhou and Ningbo contribution rates of land resource to synthetic carrying capacity were grouped into three stages, and there were two milestones trends and changes in 1996 and 2004, respectively. This study demonstrated that geographic information system and relative carrying capacity of resources are effective for assessment of region sustainable development, and provide policy guidelines for decision-making.