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.

Fabricating a Micro Electromagnetic Actuator with High Energy Density

This paper introduces a new technology to fabricate a micro electromagnetic actuator with high energy density without an enclosed magnetic circuit. This technology includes fabricating multi-turns planar micro coils and fabricating the thick magnetic （NiFe） core on the silicon wafer. The multi-turns planar micro coils are fabricated by the electroplating method from the surface along the line and by dynamically controlling the current density of the copper electrolytes. In order to fabricate thick NiFe plating,the adhesion properties between the NiFe plating and the silicon substrates are improved by changing the surface roughness of the silicon substrates and increasing the thickness of the seed layer. Furthermore,the micro electromagnetic actuator is tested and the energy density of the actuator is evaluated by force testing. The experiments show that the microactuator is efficient in producing high magnetic energy density and high magnetic force.

Prediction Technology of Buried Water-Bearing Structures in Coal Mines Using Transient Electromagnetic Method

Buried water-conducting and water-bearing structures in front of the driving head may easily lead to water bursts in coal mines. Therefore,it is very important for the safety of production to make an accurate and timely forecast about water bursts. Based on the smoke ring effect of transient electromagnetic fields,the principle of transient electro-magnetic method used in detecting buried water-bearing structures in coal mines in advance,is discussed. Small multi-turn loop configurations used in coal mines are proposed and a field procedure of semicircular sector scanning is presented. The application of this method in one coal mine indicates that the technology has many advantages compared with others. The method is inexpensive,highly accurate and efficient. Suggestions are presented for future solutions to some remaining problems.

BERT for Conversational Question Answering Systems Using Semantic Similarity Estimation

Most of the questions from users lack the context needed to thoroughly understand the problemat hand,thus making the questions impossible to answer.Semantic Similarity Estimation is based on relating user’s questions to the context from previous Conversational Search Systems(CSS)to provide answers without requesting the user’s context.It imposes constraints on the time needed to produce an answer for the user.The proposed model enables the use of contextual data associated with previous Conversational Searches(CS).While receiving a question in a new conversational search,the model determines the question that refers tomore pastCS.Themodel then infers past contextual data related to the given question and predicts an answer based on the context inferred without engaging in multi-turn interactions or requesting additional data from the user for context.This model shows the ability to use the limited information in user queries for best context inferences based on Closed-Domain-based CS and Bidirectional Encoder Representations from Transformers for textual representations.

R&D of High Current Balance Reactors

The design of high current balance reactors used in the ITER DC testing platform is presented,which is verified by simulations with finite element method software,and the reactors are fabricated and tested according to the design output.These reactors are chosen as multilayer multi-turn structure and cooled by water.The multilayer multi-turn structure is usually selected by some high voltage reactors,but is seldom used in high current situations.The analysis and testing results indicate that the multilayer multi-turn structure is also feasible for high current reactors with many advantages,and is of considerable significance to similar applications.

Design study for a 500 MeV proton synchrotron with CSNS linac as an injector

Using the China Spallation Neutron Source（CSNS） linac as the injector, a 500 MeV proton synchrotron is proposed for multidisciplinary applications, such as biology, material science and proton therapy. The synchrotron will deliver proton beam with energy from 80 MeV to 500 MeV. A compact lattice design has been worked out, and all the important beam dynamics issues have been investigated. The 80 MeV H-beam is stripped and injected into the synchrotron by using multi-turn injection. In order to continuously extraction the proton with small beam loss,an achromatic structure is proposed and a slow extraction method with RF knock-out is adopted and optimized.

An Evaluation of Chinese Human-Computer Dialogue Technology

There is a growing interest in developing human-computer dialogue systems which is an important branch in the field of artificial intelligence(AI).However,the evaluation of large-scale Chinese human-computer dialogues is still a challenging task.To attract more attention to dialogue evaluation work,we held the fourth Evaluation of Chinese Human-Computer Dialogue Technology(ECDT).It consists of few-shot learning in spoken language understanding(SLU)(Task 1)and knowledge-driven multi-turn dialogue competition(Task 2),the data sets of which are provided by Harbin Institute of Technology and Tsinghua University.In this paper,we will introduce the evaluation tasks and data sets in detail.Meanwhile,we will also analyze the evaluation results and the existing problems in the evaluation.