• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.115-118
• /
• 2020

딥러닝은 자연어처리 분야에서 우수한 성능을 보이고 있다. 하지만 우수한 성능을 달성하려면 많은 학습 데이터와 오랜 학습 시간이 필요하다. 우리는 딥러닝과 기호 규칙을 함께 사용하는 뉴럴-심볼릭 방법을 이용하여 딥러닝만으로 학습한 모델의 성능을 능가하는 방법을 제안한다. 딥러닝의 한계를 극복하기 위해서 관계추출에서 규칙 결과와 딥러닝 결과와의 불일치도를 추가한 구조를 설계하였다. 제안한 구조는 한국어 데이터에 대해서 우수한 성능을 보였으며, 빠른 성능 수렴이 이루어지는 것을 확인하였다.

• The korean journal of orthodontics
• /
• v.31 no.2 s.85
• /
• pp.187-197
• /
• 2001

The change of the vertical dimension is of fundamental importance to the orthodontist. However, the choice between the two methods of treatment, extraction versus nonextraction, is not clear. It is not verified that the extraction method decreases vertical dimension, or nonextraction methods result in an increase in vertical dimension. The purpose of this study was to evaluate the changes of vertical dimension of face after the orthodontic treatment with standard edgewise technique, and to compare them in relation to facial types and bicuspid extraction. The subjects consisted of 165 orthodontic patients (77 of adolescents, 88 of adults), and was divided into vertical nonextraction (VN) group, vertical extraction (VE) group, horizontal nonextraction (HN) group, horizontal extraction (HE) group. Pre-and Post-treatment cephalograms were taken with standard method, traced, and digitized for each subject. The comparison of the measurements were statistically executed with Student's t-test. The results were as follows : 1. The facial height and molar height were increased after orthodontic treatment in the all groups. 2. No significant difference was found in the facial height change between the vertical and horizontal groups. 3. No significant difference was found in the facial height change between the extraction and nonextraction groups. 4. As the upper molars were extruded in adolescents group and lower molars were extruded in adults group, lower anterior facial height (LAFH) was increased. 5. None of the pretreatment variables correlates to the change of lower anterior facial height (LAFH).

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Journal of the Korean Society for Library and Information Science
• /
• v.39 no.2
• /
• pp.287-304
• /
• 2005

The goal of this research is to evaluate the usability of visually browsing the automatically extracted information. A domain-independent information extraction system was used to extract information from news type texts to populate the visually browasable knowledge base. The information extraction system automatically generated Concept-Relation-Concept triples by applying various Natural Language Processing techniques to the text portion of the news articles. To visualize the information stored in the knowledge base, we used PersoanlBrain to develop a visualization portion of the user interface. PersonalBrain is a hyperbolic information visualization system, which enables the users to link information into a network of logical associations. To understand the usability of the visually browsable knowledge base, IS test subjects were observed while they use the visual interface and also interviewed afterward. By applying a qualitative test data analysis method. a number of usability Problems and further research directions were identified.

• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.73-85
• /
• 2011

Lots of valuable textual information is used to extract relations between named entities from literature. Composite kernel approach is proposed in this paper. The composite kernel approach calculates similarities based on the following information:(1) Phrase structure in convolution parse tree kernel that has shown encouraging results. (2) Predicate-argument structure patterns. In other words, the approach deals with syntactic structure as well as semantic structure using a reciprocal method. The proposed approach was evaluated using various types of test collections and it showed the better performance compared with those of previous approach using only information from syntactic structures. In addition, it showed the better performance than those of the state of the art approach.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.46 no.4
• /
• pp.235-239
• /
• 2020

Objectives: Preoperative nervousness and anxiety are frequently encountered by individuals who undergo extractions of impacted wisdom teeth. The aim of the present study is to evaluate salivary alpha amylase (sAA) level in patients for assessment of stress during third molar surgery while listening to piano music and to determine its co-relation with pain catastrophizing scale (PCS). Materials and Methods: Seven patients (four males and three females) indicated for surgical extraction of bilaterally impacted mandibular third molars were included. Pre-surgical patient assessments were completed, and three samples of saliva were collected during surgery-one at baseline, one 30 minutes after commencement of surgery, and one after suturing. Assessment was performed on both sides separately with and without piano music, and the samples were assessed for sAA level and correlated with the patient's self-reported PCS. Results: Statistically significant results were obtained in patients who underwent surgical extraction while listening to piano music (P=0.046). The correlation of sAA level with PCS was not significant. Conclusion: Music demonstrated a beneficial effect on lowering the levels of stress and anxiety that a patient exhibits during any surgical procedure, and sAA can be a useful biomarker for similar assessments.

• The Journal of Korean Association of Computer Education
• /
• v.15 no.2
• /
• pp.9-18
• /
• 2012

This study investigated the extraction algorithm fitting for variables of adolescents' computer use type with the sample from KYPS data (3409 in the second grade of the junior high school; 1704 boys and 1705 girls). The results of the decision tree model revealed that : (1) Gender, computer use time, misdeed friends, parent supervision, other agreement of misdeed, parent study expectation, self-control, teacher attachment, and sibling relation were significant for entertainment type. (2) Gender, cyberclub, computer use time, self-belief, online misdeed were significant for relation type. (3) Study enthusiasm, personal study time, optimistic disposition, study and spare time, cyberclub, self-belief, and other people criticism were significant for information type. These results suggest that adolescents' diverse conditions should be considered for using computer more efficiently.

• Journal of Korean Institute of Industrial Engineers
• /
• v.29 no.1
• /
• pp.49-64
• /
• 2003

Although assembly sequence planning is an essential task in assembly process planning, it is known as one of the most difficult and time consuming jobs because its complexity is increased geometrically when the number of parts in an assembly is increased. The purpose of this study is to develop a more efficient algorithm for generating assembly sequences automatically. By considering subassemblies, a new heuristic method generates a preferred parallel assembly sequence that can be used in robotic assembly systems. A parallel assembly sequence concept provides a new representation scheme for an assembly in which the assembly sequence precedence information is not required. After an user inputs both the directional mating relation information and the mating condition information, an assembly product is divided into subgroups if the product has cut-vertices. Then, a virtual disassembly process is executed to generate alternate parallel assembly sequences with intermediate assembly stability. Through searching parts relations in the virtual disassembly process, stable subassemblies are extracted from translation-free parts along disassembling directions and this extraction continues until no more subassemblies are existed. Also, the arithmetic mean parallelism formula as a preference criterion is adapted to select the best parallel assembly sequence among others. Finally a preferred parallel assembly sequence is converted to an assembly BOM structure. The results from this study can be utilized for developing CAAPP(Computer-Aided Assembly Process Planning) systems as an efficient assembly sequence planning algorithm.

• The Journal of Society for e-Business Studies
• /
• v.24 no.3
• /
• pp.87-98
• /
• 2019

As artificial intelligence is actively studied, it is being applied to various fields such as image, video and natural language processing. The natural language processing, in particular, is being studied to enable computers to understand the languages spoken and spoken by people and is considered one of the most important areas in artificial intelligence technology. In natural language processing, it is a complex, but important to make computers learn to understand a person's common sense and generate results based on the person's common sense. Knowledge graphs, which are linked using the relationship of words, have the advantage of being able to learn common sense easily from computers. However, the existing knowledge graphs are organized only by focusing on specific languages and fields and have limitations that cannot respond to neologisms. In this paper, we propose an intelligent chatbotsystem that collects and analyzed data in real time to build an automatically scalable knowledge graph and utilizes it as the base data. In particular, the fine-tuned BERT-based for relation extraction is to be applied to auto-growing graph to improve performance. And, we have developed a chatbot that can learn human common sense using auto-growing knowledge graph, it verifies the availability and performance of the knowledge graph.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.21 no.5
• /
• pp.1307-1312
• /
• 2007

This study was designed to investigate effectiveness of korean medicine therapy and the relation between effectiveness of that and single nucleotide gene polymorphism in stroke patients. This study was carried out on 92 stroke patients who were admitted to the department of acupuncture & moxibustion, college of Oriental medicine, Daegu Haany University and 112 healthy Korean. All patients were received Korean medicine therapy including acupuncture and herbal medicine for stroke and assessed by National Institutes of Health Stroke Scale(NIHSS). Blood samples from all subjects were obtained for DNA extraction. The extracted DNA was amplified by polymerase chain reaction(PCR). PCR products were visualized by 1.5% agarose gel electrophoresis. Through Pyrosequencing of PCR product, the polymorphism of single nucleotide gene was genotyped automatically. There were significant difference between before and after Korean medicine therapy in NIHSS. Genotypes were AA, AG, GG, but there was no significant difference between control and stroke groups. And there was not any statistical significant allelic frequency difference between control and stroke groups. We concluded that Korean medicine therapy in stroke patient can improve NIHSS, but there is no definite relation between effectiveness of Korean medicine therapy and single nucleotide gene polymorphism in stroke patients. This study need to be confirmed in large patients and further studies about relation with gene polymorphism are required.