• The Journal of the Korea Contents Association
• /
• v.19 no.7
• /
• pp.427-435
• /
• 2019

Soundscape provides important resources to understand social and cultural aspects of our society, however, it is still its infancy to study on the research framework to record, conserve, categorize, and analyze soundscapes. Topic modeling is an automatic approach to discover hidden themes that are disperse in unstructured documents, thus topic modeling is robust enough to find latent topics such as research trends behind a collection of documents. The purpose of this paper is to discover topics on current soundscape research based on topic modeling, furthermore, to discuss the possibilities to design a metadata system for sound archives and to improve Soundscape Ontology which is currently developing.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.6
• /
• pp.402-411
• /
• 2005

Context-aware engineering services in ubiquitous environments are emerging as a viable alternative to traditional engineering services. Most of the previous approaches are computer-centered rather than human-centered. In this paper, we present a Ubiquitous and Context-Aware computing Framework for collaborative virtual Engineering $(U-CAF\acute{E})$ services. The proposed approach utilizes BPEL-based (Business Process Execution Language) process templates for engineering service orchestration and choreography and adopts semantic web-based context-awareness for providing human-centered engineering services. The paper discusses how to utilize engineering contexts and share this knowledge in support of collaborative virtual engineering services and service interfaces. The paper also discusses how Web services and JINI (Java Intelligent Network Infrastructure) services are utilized to support engineering service federations and seamless Interactions among persons, devices, and various kinds of engineering services.

• ETRI Journal
• /
• v.38 no.3
• /
• pp.487-493
• /
• 2016

Two new methods are proposed for an unsupervised adaptation of a language model (LM) with a single sentence for automatic transcription tasks. At the training phase, training documents are clustered by a method known as Latent Dirichlet allocation (LDA), and then a domain-specific LM is trained for each cluster. At the test phase, an adapted LM is presented as a linear mixture of the now trained domain-specific LMs. Unlike previous adaptation methods, the proposed methods fully utilize a trained LDA model for the estimation of weight values, which are then to be assigned to the now trained domain-specific LMs; therefore, the clustering and weight-estimation algorithms of the trained LDA model are reliable. For the continuous speech recognition benchmark tests, the proposed methods outperform other unsupervised LM adaptation methods based on latent semantic analysis, non-negative matrix factorization, and LDA with n-gram counting.

• East Asian mathematical journal
• /
• v.40 no.3
• /
• pp.307-318
• /
• 2024

This paper explores the application of matrix factorization, specifically CUR decomposition, in the clustering of Korean language documents by topic. It addresses the unique challenges of Natural Language Processing (NLP) in dealing with the Korean language's distinctive features, such as agglutinative words and morphological ambiguity. The study compares the effectiveness of Latent Semantic Analysis (LSA) using CUR decomposition with the classical Singular Value Decomposition (SVD) method in the context of Korean text. Experiments are conducted using Korean Wikipedia documents and newspaper data, providing insight into the accuracy and efficiency of these techniques. The findings demonstrate the potential of CUR decomposition to improve the accuracy of document clustering in Korean, offering a valuable approach to text mining and information retrieval in agglutinative languages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.392-412
• /
• 2018

Due to the semantic gap problem across different modalities, automatically retrieval from multimedia information still faces a main challenge. It is desirable to provide an effective joint model to bridge the gap and organize the relationships between them. In this work, we develop a deep image annotation and classification by fusing multi-modal semantic topics (DAC_mmst) model, which has the capacity for finding visual and non-visual topics by jointly modeling the image and loosely related text for deep image annotation while simultaneously learning and predicting the class label. More specifically, DAC_mmst depends on a non-parametric Bayesian model for estimating the best number of visual topics that can perfectly explain the image. To evaluate the effectiveness of our proposed algorithm, we collect a real-world dataset to conduct various experiments. The experimental results show our proposed DAC_mmst performs favorably in perplexity, image annotation and classification accuracy, comparing to several state-of-the-art methods.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.153-167
• /
• 2019

This study aims to identify the media agenda and to compare each media agenda by media and by time period, analyzing the news about 2019 Gangwon-do's wild fire reported by 37 Korean news media. Using the topic modeling algorithm and semantic network analysis, this study inspected the configuration of the network media agenda and examined the intermedia agenda setting effect by using QAP correlation analysis. Results showed that the sensational media agenda with the attributes such as victim aid and political conflict and the similarity of each media agenda for this disaster reporting.

• Language and Information
• /
• v.11 no.1
• /
• pp.1-23
• /
• 2007

This study aims to research into the meaning of Korean particle 'ka' and 'nun' inductively by examining the correspondences of those particles and English articles on the Korean-English parallel corpus. The correspondences were checked in three ways: semantically, syntactically and pragmatically. This study found that when the semantic or syntactic tier is not salient, the pragmatic tier is activated and particles are selected according to the pragmatic elements such as the amount of information or the change of topic. However, if the meaning of the particles is salient or if there is any syntactic motive, particles are selected in accordance with the semantic or syntactic elements. Former studies which focused on one of those three tiers cannot properly explain such correspondences on the Korean-English parallel corpus. This study shows that semantic, syntactic and pragmatic tiers hierarchically affect the selection of a particle and that the selection process is also related to speaker's intention. This dimensional analysis of particles is expected to contribute to theoretical studies and applied studies like Korean language education as well.

• Journal of the Regional Association of Architectural Institute of Korea
• /
• v.21 no.5
• /
• pp.109-116
• /
• 2019

The Seoul city recommended that old apartments be preserved, and as part of that, it decided to preserve some of the buildings for Jamsil Jugong, which was built in 1977, and Gaepo Jugong, which was constructed in 1981. The purpose of this study was to compare and review newspaper articles with two perspectives positive and negative about how the social perception of 'apartment trace remaining' was being constructed. By looking at the meaning of keywords delivered by newspaper articles and the interaction structure between keywords through the analysis of semantic networks, we analyzed how the media is pursuing an issue on the topic of preservation of architectural cultural heritage. The analysis results confirmed that there was a clear difference between positive and negative newspaper. Positive articles dealt with utilization from the point of view of keywords linked to preservation, and negative articles showed that keywords related to the property and backlash of residents linked to the policy of the Seoul Metropolitan Government were linked, leading to high negative public opinion.

• Journal of the Korean Society for Library and Information Science
• /
• v.41 no.2
• /
• pp.291-316
• /
• 2007

The purpose of this study is to design metadata model for describing different kinds of concepts, properties, and semantic relationships of result materials of researches. We examine our metadata model to evaluate correctness and efficiency of the model through contents analysis of a constructed database. From the results of examination, we suggest more effective structure of metadata schema. Domain ontology could constructed by the enlarged thesaurus in order to overcome the limitation of the keyword search, therefore we design a philosophy and religion ontology based on subject classification to improve information retrieval and implement it using XML/Topic Maps to improve retrieval functionality of our database.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.2
• /
• pp.127-132
• /
• 2022

In the era of COVID-19 pandemic, COVID related keywords, news and SNS data are pouring out. With the help of the data and LDA topic modeling, we can check out what media reports about COVID-19 and vaccines. Also, we can be clear how the public reacts to the vaccine on social media and how this is related with the increasing number of COVID-19 patients. By using sentimental analysis methodology, we can get to know about the different kinds of reports that Korea media send out and get to know what kind of emotions that each media company uses in majority. Through this procedure, we can know the difference between the Korean media and the foreign ones. Ultimately, we can find and analyze the keyword that suddenly rose during the COVID-19 period throughout this research.