• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.58-66
• /
• 2019

Recognition of named entity such as proper nouns in conversation sentences is the most fundamental and important field of study for efficient conversational information prediction. The most important part of a task-oriented dialogue system is to recognize what attributes an object in a conversation has. The named entity recognition model carries out recognition of the named entity through the preprocessing, word embedding, and prediction steps for the dialogue sentence. This study aims at using user - defined dictionary in preprocessing stage and finding optimal parameters at word embedding stage for efficient dialogue information prediction. In order to test the designed object name recognition model, we selected the field of daily chemical products and constructed the named entity recognition model that can be applied in the task-oriented dialogue system in the related domain.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.206-208
• /
• 2022

As the big data industry has recently developed significantly, interest in privacy violations caused by personal information leakage has increased. There have been attempts to automate this through named entity recognition in natural language processing. In this paper, named entity recognition data is constructed semi-automatically by identifying sentences with de-identification information from de-identification information in Korean Wikipedia. This can reduce the cost of learning about information that is not subject to de-identification compared to using general named entity recognition data. In addition, it has the advantage of minimizing additional systems based on rules and statistics to classify de-identification information in the output. The named entity recognition data proposed in this paper is classified into twelve categories. There are included de-identification information, such as medical records and family relationships. In the experiment using the generated dataset, KoELECTRA showed performance of 0.87796 and RoBERTa of 0.88.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.55-62
• /
• 2017

The Named Entity Recognition system is a system that recognizes words or phrases with object names such as personal name (PS), place name (LC), and group name (OG) in the document as corresponding object names. Traditional approaches to named entity recognition include statistical-based models that learn models based on hand-crafted features. Recently, it has been proposed to construct the qualities expressing the sentence using models such as deep-learning based Recurrent Neural Networks (RNN) and long-short term memory (LSTM) to solve the problem of sequence labeling. In this research, to improve the performance of the Korean named entity recognition system, we used a hand-crafted feature, part-of-speech tagging information, and pre-built lexicon information to augment features for representing sentence. Experimental results show that the proposed method improves the performance of Korean named entity recognition system. The results of this study are presented through github for future collaborative research with researchers studying Korean Natural Language Processing (NLP) and named entity recognition system.

• Journal of Distribution Science
• /
• v.14 no.2
• /
• pp.57-63
• /
• 2016

Purpose - The present study aimed to investigate the difference between entity theorists and incremental theorists in the extent of attributing efforts and traits of consumers for the realization of pursued goals. Furthermore, the present study was conducted to determine the difference depending on circumstances. In this regard, the circumstances where consumers felt pride were divided into those in which important goals and ordinary life goals were achieved. Research design, data, and methodology - An empirical study was performed, which was divided into group 1 and 2. Group 1 is the experimental group concerned with the important goal achievement, and group 2 is the control group related to daily ordinary goal achievement. 80 college students were assigned to each group, respectively. The empirical study for each of the two groups was performed respectively by means of questionnaire survey. In the experimental group, t-test was used to verify the hypotheses for the empirical study. In the circumstances of the control group, t-test was also used to examine whether the results were same as those shown from the analysis of experimental group data or not. Results - According to the group 1 and 2, the t-test of the empirical study showed that entity theorists tended to attribute the achievements of goals to their traits more than incremental theorists did, whereas the incremental theorists tended to attribute achievements of goals to their efforts more than entity theorists did in the important goals-achieved circumstance. In the circumstance of daily life goals-achieved, additional questionnaire survey and analysis were conducted, however, there was no difference between incremental and entity theorists in regard to attributing realization of goals to their efforts, and it leads to assess the difference in the meaning of invested efforts between important goal and ordinary goal achievement. Conclusions - Considering that the feeling of consumers has been regarded as one of the significant factors in marketing mix management, the results of this study are considered as significant implications for management. The implications can be said that when incremental consumers feel authentic pride in the important goals-achieved circumstance, marketers are requested to emphasize the fact that the efforts of consumers have contributed to realization of the important goals. By contrast, when consumers feel hubristic pride in both circumstances, marketers are requested to approach to entity-oriented consumers by way of trait. Authentic and hubristic pride are pervasive and engendered by important events or daily routines, and they could have effect on delaying making decisions. Therefore, it is necessary for future research to examine the unexplored difference of effect between incidental authentic and hubristic pride on consumer's self-control. In particular, future researches are related to the extent of difference in attributing efforts and traits. The consumers'realization for the previously pursued goals between entity theorists and incremental theorists affects their present or long distant decisions in self-control dilemmas. The consumers are faced with choosing one between virtuous long term- related option and vice immediate option.

• Korean Journal of Cognitive Science
• /
• v.27 no.1
• /
• pp.27-41
• /
• 2016

Named entity recognition is to classify elements in text into predefined categories and used for various departments which receives natural language inputs. In this paper, we propose a method which can generate named entity training corpus automatically using knowledge bases. We apply two different methods to generate corpus depending on the knowledge bases. One of the methods attaches named entity labels to text data using Wikipedia. The other method crawls data from web and labels named entities to web text data using Freebase. We conduct two experiments to evaluate corpus quality and our proposed method for generating Named entity recognition corpus automatically. We extract sentences randomly from two corpus which called Wikipedia corpus and Web corpus then label them to validate both automatic labeled corpus. We also show the performance of named entity recognizer trained by corpus generated in our proposed method. The result shows that our proposed method adapts well with new corpus which reflects diverse sentence structures and the newest entities.

• The Journal of Korean Association of Computer Education
• /
• v.18 no.6
• /
• pp.81-88
• /
• 2015

Along with advent of Web 3.0 era and advanced technologies of IoT(Internet of Things), massive amounts of information are generated. Reflecting this trend, this paper developed a semi-automatic construction tool for named entity dictionary based on active learning. Our proposed method chose error candidates to verify among the preliminary results using initial trained model and re-trained the model for correctly labeled data by user. We adopt active learning approach for minimizing human effort utilized metadata features of Wikipedia. Based on experimental results using our tool, we show that 68.6% errors were automatically corrected.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.253-256
• /
• 2009

This paper describes a vertical search system based on multiple entity-centric unification, which enables to deal with the search queries including multiple domains. To implement the system, we introduced two search technologies; one is for merging service components dynamically according to the entities in the search keywords, and the other is for searching fields with appropriate entities. Our current system includes about 453,000 overseas journal papers for article information search and two entity types; research topic and researcher.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.197-202
• /
• 2019

XML has been established as a de facto standard for representing and exchanging documents, and has been widely used as a logical data model. Using XML as a logical database model, it requires a conceptual model for the semantics that XML has. However, the existing conceptual models, such as Entity Relationship models and UML, have been extended their concepts to express the specific characteristics of XML, but so far, there are no standard models. This paper compares the characteristics of the typical model of conceptual model of XML by Extended Entity Relationship model from the perspective of database field. For this, we propose the requirements that must be met for XML, and on the basis of these requirements, the approaches of each model are compared.

• Journal of Korea Multimedia Society
• /
• v.4 no.6
• /
• pp.543-553
• /
• 2001

In this paper, we proposed management strategy of medical image data in order to solve the problem in traditional medical images migration method. As management strategy of medical image data we proposed EAT(Expanded Average Transaction time) data migration method and data storing method based on temporal interrelation. In EAT data migration strategy, we define the dividing criterion which distinguish entity versions to be stored in each storage and also define entity versions to be stored in each storage. We defined degree of overlap and degree of difference for any two entity versions, and integrated those values and described method which place entity versions to storage. In order to compare the number of cluster references when we change rate of temporal queries, the number of cluster references of proposed method is smaller than that of traditional method.

• Korean Institute of Interior Design Journal
• /
• v.22 no.5
• /
• pp.199-206
• /
• 2013

Design is one of diverse human communication activities. Development of technologies has led to execution of more active design communication functions, stirring social and cultural changes. The concept of design communication has become stronger by overcoming the limitations of verbal communication and expanding the methods of communication. These social changes are highlighted In the design of modern space. Even though communication in interior design activities is so important, detailed studies on communication of each entity are still very insufficient. Design communication refers to tools and activities for overall communications in the design process. In design activities, relevant communication is indispensible. Therefore, studies on practical communication methods are essential for accurate communication of content that has to be shared in the results or in the process of obtaining the results, rather than only focusing on the future techniques and functions of design. In other words, improving the efficiency of interior design communication requires establishing a communication relationship structure of each entity, which calls for proper expression methods depending on each entity. Therefore, this study is aimed at exploring efficient expression methods in line with the relationship structure of each entity in the interior design process.