• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.229-236
• /
• 2003

Named entity recognition is the process indispensable to question answering and information extraction systems. This paper presents an HMM based named entity (m) recognition method using the construction principles of compound words. In Korean, many named entities can be decomposed into more than one word. Moreover, there are contextual relationships among nouns in an NE, and among an NE and its surrounding words. In this paper, we classify words into a word as an NE in itself, a word in an NE, and/or a word adjacent to an n, and train an HMM based on NE-related word types and parts of speech. Proposed named entity recognition (NER) system uses trigram model of HMM for considering variable length of NEs. However, the trigram model of HMM has a serious data sparseness problem. In order to solve the problem, we use multi-level back-offs. Experimental results show that our NER system can achieve an F-measure of 87.6% in the economic articles.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.18 no.3
• /
• pp.233-244
• /
• 2015

Marine ecosystem modelling has become a more widely used decision-making tool in coastal ecosystem-based management. However, it is not trivial to develop a well calibrated/validated model with potential applicability and practicality because understanding ecological processes with complexities is a pre-requisite for developing robust ecosystem models and this accompanies a great deal of well coordinated efforts among field-going ecologists, laboratory scientists, modelers, stake-holders and managers. This report aims to provide a brief introduction on two different approaches in marine ecological models: deterministic (mechanistic) and stochastic (statistical) approach. We also included definitions, historical overview of past researches, case studies, and contextual suggestions for coastal management in Korea. A long list of references this report included in this study might be used as an introductory material for those who wish to enter ecosystem modelling field.

• Korea journal of population studies
• /
• v.34 no.2
• /
• pp.135-162
• /
• 2011

Given the 4 contexts-parents, friends, teachers and community- of adolescents, this research verified the casual relationships between each contextual support and the suicidal impulse, and the gender difference. The 4-year longitudinal data(KYPS) collected from 3,697 adolescents were used in this study. Using the Autoregressive Cross-Lagged Model, the suicidal impulse was consistently present from the 3rd grade in middle school to the 3rd grade in high school with significant stability. Gender differences were founded in the effect of parental support among the 3rd grade in middle school. Also the negative effect of friends' support on the suicidal impulse among the first grade high school students. The effects were more stronger for girls than boys. Previous supports by teachers and community had no significant effects on later suicidal impulses. These results suggest that the study of suicidal impulse needs to examine the complex support system of multiple context layers.

• The Journal of Society for e-Business Studies
• /
• v.12 no.2
• /
• pp.111-132
• /
• 2007

Developing and managing Web applications are more complex than ever because of their growing functionalities, advancing Web technologies, increasing demands for integration with legacy applications, and changing content and structure. All these factors call for a more inclusive and comprehensive Web application design method. In response, we propose a context-based Web application design methodology that is based on several classification schemes including a Webpage classification, which is useful for identifying the information delivery mechanism and its relevant Web technology; a link classification, which reflects the semantics of various associations between pages; and a software component classification, which is helpful for pinpointing the roles of various components in the course of design. The proposed methodology also incorporates a unique Web application model comprised of a set of information clusters called compendia, each of which consists of a theme, its contextual pages, links, and components. This view is useful for modular design as well as for management of ever-changing content and structure of a Web application. The proposed methodology brings together all the three classification schemes and the Web application model to arrive at a set of both semantically cohesive and syntactically loose-coupled design artifacts.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.57-66
• /
• 2022

In this paper, we propose a legal document search method that uses the Sentence-BERT model. The general public who wants to use the legal search service has difficulty searching for relevant precedents due to a lack of understanding of legal terms and structures. In addition, the existing keyword and text mining-based legal search methods have their limits in yielding quality search results for two reasons: they lack information on the context of the judgment, and they fail to discern homonyms and polysemies. As a result, the accuracy of the legal document search results is often unsatisfactory or skeptical. To this end, This paper aims to improve the efficacy of the general public's legal search in the Supreme Court precedent and Legal Aid Counseling case database. The Sentence-BERT model embeds contextual information on precedents and counseling data, which better preserves the integrity of relevant meaning in phrases or sentences. Our initial research has shown that the Sentence-BERT search method yields higher accuracy than the Doc2Vec or TF-IDF search methods.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.325-334
• /
• 2023

Computer vision-based damage detection enables non-contact, efficient and low-cost bridge health monitoring, which reduces the need for labor-intensive manual inspection or that for a large number of on-site sensing instruments. By leveraging recent semantic segmentation approaches, we can detect regions of critical structural components and identify damages at pixel level on images. However, existing methods perform poorly when detecting small and thin damages (e.g., cracks); the problem is exacerbated by imbalanced samples. To this end, we incorporate domain knowledge to introduce a hierarchical semantic segmentation framework that imposes a hierarchical semantic relationship between component categories and damage types. For instance, certain types of concrete cracks are only present on bridge columns, and therefore the noncolumn region may be masked out when detecting such damages. In this way, the damage detection model focuses on extracting features from relevant structural components and avoid those from irrelevant regions. We also utilize multi-scale augmentation to preserve contextual information of each image, without losing the ability to handle small and/or thin damages. In addition, our framework employs an importance sampling, where images with rare components are sampled more often, to address sample imbalance. We evaluated our framework on a public synthetic dataset that consists of 2,000 railway bridges. Our framework achieves a 0.836 mean intersection over union (IoU) for structural component segmentation and a 0.483 mean IoU for damage segmentation. Our results have in total 5% and 18% improvements for the structural component segmentation and damage segmentation tasks, respectively, compared to the best-performing baseline model.

• SUVANNABHUMI
• /
• v.8 no.2
• /
• pp.131-159
• /
• 2016

This qualitative study was designed to explore the definition of ethnic identity of the Dusuns in Brunei Darussalam from the perspective of Shamsul A.B.'s (1996) "everyday-defined" social reality. The purpose of this study was twofold. Firstly, by employing Phinney's (1996) formulation of ethnic identity, this study examined the existence of core components of ethnic identity, namely, ethnic self-identification, ethnic involvement, positive attitude towards ethnic group, and sense of belonging in the life of the Dusuns. Secondly, by utilizing Phinney's (1996) three-stage model of ethnic identity formation, this study investigated the relationship between core components and the formation process of ethnic identity. Twenty-six Dusun informants ranging in age from 8 to 80 years old were interviewed for the purpose of this study. The analysis of the interview data revealed that all core components exist and evolve in the life of the Dusuns. Different perspectives towards core components can also be identified across different age groups. Adult informants contested the relevance of ethnic involvement in view of socio-cultural transformations that occurred within the ethnic group, whereas younger Dusuns were not able to extend sense of belonging outside their family. These findings lead to the identification of family and historical contexts as influential factors that shape the ways the informants experienced the ethnic identity components. Further, the findings of this study indicate the relationship between core components and the formation process of ethnic identity. Sense of belonging and community is only evident in the experience of older informants, sufficient to help them reach the stage of achieving ethnic identity. This also shows a positive sequential relation between the stages in Phinney's ethnic identity model and the age of the informants. Interestingly, evidence on internalized sense of belonging reveals the fact that an individual could still attain ethnic identity achievement even without experiencing all components of ethnic identity. Once again, this study suggests contextual factors play a role in the stage progression of the Dusuns' ethnic identity.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.9-21
• /
• 2024

Deep learning has been developing rapidly in recent years, with many researchers working to utilize large language models in various domains. However, there are practical difficulties that developing and utilizing language models require massive data and high-performance computing resources. Therefore, in-context learning, which utilizes prompts to learn efficiently, has been introduced, but there needs to be clear criteria for effective prompts for learning. In this study, we propose a methodology for enhancing prompt-based learning performance by improving the PET technique, which is one of the contextual learning methods, to select PVPs that are similar to the context of existing data. To evaluate the performance of the proposed methodology, we conducted experiments with 30,100 restaurant review datasets collected from Yelp, an online business review platform. We found that the proposed methodology outperforms traditional PET in all aspects of accuracy, stability, and learning efficiency.

• Asia Pacific Journal of Corpus Research
• /
• v.5 no.1
• /
• pp.23-36
• /
• 2024

This research centers on the Taiwan Eye-Movement Corpus of Spanish (TECS), a specially created corpus comprising eye-tracking data from Chinese-speaking learners of Spanish as a third language in Taiwan. Its primary purpose is to explore the broad utility of TECS in understanding language learning processes, particularly the initial stages of language learning. Constructing this corpus involves gathering data on eye-tracking, reading comprehension, and language proficiency to develop a machine-learning model that predicts learner behaviors, and subsequently undergoes a predictability test for validation. The focus is on examining attention in input processing and their relationship to language learning outcomes. The TECS eye-tracking data consists of indicators derived from eye movement recordings while reading Spanish sentences with temporal references. These indicators are obtained from eye movement experiments focusing on tense verbal inflections and temporal adverbs. Chinese expresses tense using aspect markers, lexical references, and contextual cues, differing significantly from inflectional languages like Spanish. Chinese-speaking learners of Spanish face particular challenges in learning verbal morphology and tenses. The data from eye movement experiments were structured into feature vectors, with learner behaviors serving as class labels. After categorizing the collected data, we used two types of machine learning methods for classification and regression: Random Forests and the k-nearest neighbors algorithm (KNN). By leveraging these algorithms, we predicted learner behaviors and conducted performance evaluations to enhance our understanding of the nexus between learner behaviors and language learning process. Future research may further enrich TECS by gathering data from subsequent eye-movement experiments, specifically targeting various Spanish tenses and temporal lexical references during text reading. These endeavors promise to broaden and refine the corpus, advancing our understanding of language processing.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.