• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3168-3186
• /
• 2020

Automatic topic essay generation (TEG) is a controllable text generation task that aims to generate informative, diverse, and topic-consistent essays based on multiple topics. To make the generated essays of high quality, a reasonable method should consider both diversity and topic-consistency. Another essential issue is the intrinsic link of the topics, which contributes to making the essays closely surround the semantics of provided topics. However, it remains challenging for TEG to fill the semantic gap between source topic words and target output, and a more powerful model is needed to capture the semantics of given topics. To this end, we propose a pretraining-based contextual self-attention (PC-SAN) model that is built upon the seq2seq framework. For the encoder of our model, we employ a dynamic weight sum of layers from BERT to fully utilize the semantics of topics, which is of great help to fill the gap and improve the quality of the generated essays. In the decoding phase, we also transform the target-side contextual history information into the query layers to alleviate the lack of context in typical self-attention networks (SANs). Experimental results on large-scale paragraph-level Chinese corpora verify that our model is capable of generating diverse, topic-consistent text and essentially makes improvements as compare to strong baselines. Furthermore, extensive analysis validates the effectiveness of contextual embeddings from BERT and contextual history information in SANs.

• Journal of Engineering Education Research
• /
• v.21 no.1
• /
• pp.14-26
• /
• 2018

The goal of this study was to explore topic defining patterns of students in interdisciplinary Capstone Design Class. Thematic analysis methodology was used to examine 85 Korean college students' lived experience of project topic generation which is for interdisciplinary capstone design class and Individual open-ended survey for constituted the data sources. Findings show four contexts of student's topic defining patterns using thematic analysis including (a) one leader's directed problem representation, (b) team common decision making after brainstorming, (c) empathy with professor proposed issue, (d) problems offered to students by corporate or research competitions. Based on research result, I could suggest instructional strategies of Capstone Design Class of teacher for helping their students' topic defining. It was necessary to minimize the opinions of the instructors at the beginning of class and minimize the number of team members. And also it provided a lot of opportunities to collaborate with companies in the topic selection process, it will help to develop the students' ability to determine the valuable topic in project.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.193-205
• /
• 2021

The AI speaker market is growing steadily. However, the satisfaction of actual users is only 42%. Therefore, in this paper, we collected reviews on Amazon Echo Dot 3rd and 4th generation models to analyze what hinders the user experience through the topic changes and emotional changes of each generation of AI speakers. By using topic modeling analysis techniques, we found changes in topics and topics that make up reviews for each generation, and examined how user sentiment on topics changed according to generation through deep learning-based sentiment analysis. As a result of topic modeling, five topics were derived for each generation. In the case of the 3rd generation, the topic representing general features of the speaker acted as a positive factor for the product, while user convenience features acted as negative factor. Conversely, in the 4^th generation, general features were negatively, and convenience features were positively derived. This analysis is significant in that it can present analysis results that take into account not only lexical features but also contextual features of the entire sentence in terms of methodology.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.730-739
• /
• 2010

One of core technology in Web 2.0 is tagging, which is applied to multimedia data such as web document of blog, image and video etc widely. But unlike expectation that the tags will be reused in information retrieval and then maximize the retrieval efficiency, unacceptable retrieval results appear owing to toot limitation of tag. In this paper, in the base of preceding research about image retrieval through tag clustering, we design and implement a topic map generation system which is a semantic knowledge system. Finally, tag information in cluster were generated automatically with topics of topic map. The generated topics of topic map are endowed with mean relationship by use of WordNet. Also the topics are endowed with occurrence information suitable for topic pair, and then a topic map with semantic knowledge system can be generated. As the result, the topic map preposed in this paper can be used in not only user's information retrieval demand with semantic navigation but alse convenient and abundant information service.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.299-308
• /
• 2006

As recently XML is becoming the standard of exchanging web documents and public documentations, XML data are increasing in many areas. To retrieve the information about XML documents efficiently, the semantic web based on the ontology is appearing. The existing ontology has been constructed manually and it was time and cost consuming. Therefore in this paper, we propose the semi-automatic ontology generation technique using the data mining technique, the association rules. The proposed method solves what type and how many conceptual relationships and determines the ontology domain level for the automatic ontology generation, using the data mining algorithm. Appying the association rules to the XML documents, we intend to find out the conceptual relationships to construct the ontology, finding the frequent patterns of XML tags in the XML documents. Using the conceptual ontology domain level extracted from the data mining, we implemented the semantic web based on the ontology by XML Topic Maps (XTM) and the topic map engine, TM4J.

• Journal of Industrial Convergence
• /
• v.20 no.1
• /
• pp.43-51
• /
• 2022

The purpose of this study is to provide basic information necessary for the establishment of mobile service marketing strategies, educational service development, and engineering education for Generation Z by analyzing the utilitization of various applications by Gen Z. To this end, 177 essays on mobile service usage experience were collected, major topics were analyzed using topic modeling, and these were visualized through word cloud analysis. As a result of the study, the main topics were related to 'transportation' such as movement and public transportation, 'personal management' such as schedule management, financial management, food management, 'transaction' such as checkout, meeting, purchase, 'leisure' such as eating out, travel, study, culture. Additionally, words such as time, thought, people, life, bus, information, confirmation, payment, KakaoTalk, and so on were found to have a high of frequency of use. Also, there was found to be a difference between topics by college. This study is meaningful in that it collected essays, which are unstructured data, and analyzed them through topic modeling.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.75-86
• /
• 2018

The DDS (Data Distribution Service) specification defines a discovery method for finding participants and endpoints in a DDS network. The standard discovery mechanism uses the multicast protocol and finds all the endpoints in the network. Because of using multicasting, discovery may fail in a network with different segments. Other problems include that memory space wastes due to storing information of all the endpoints. The Topic Name Service (TNS) solves these problems by unicasting only the endpoints, which are required for communication. However, an extra delay time is inevitable in components of TNS, i.e, a front-end server, topic name servers, and a terminal server. In this paper, we analyze the performance of TNS. Delay times in the servers of TNS and time required to receive endpoint information are measured. Time to finish discovery and number of receiving endpoints compare with the standard discovery method.

• Knowledge Management Research
• /
• v.16 no.4
• /
• pp.69-87
• /
• 2015

Given the huge number of data produced by its users, SNS is a great source of customer insights. Since viral trends in SNS reflect customers' direct feedback, companies can draw out highly meaningful business insights when such data is effectively analyzed and managed. However, while the importance of understanding SNS big data keeps growing, the methods for analyzing atypical data such as SNS postings for business insights over product has not been well studied. This study aims to demonstrate the way to exploit topic modeling method to support marketing strategy generation and therefore leverage business process. First, we conducted topic modeling analysis for twitter data of Apple and Samsung smartphones. Then we comparatively examined the analysis results to draw meaningful market insights about each smartphone product. Finally, we draw out a strategic marketing recommendation for each smartphone brand based on the findings.

• Asian Journal of Innovation and Policy
• /
• v.12 no.3
• /
• pp.345-362
• /
• 2023

As the widespread adoption and proliferation of electric vehicles continue, the secondary battery market is experiencing rapid growth. However, lithium-ion batteries, which constitute a majority of secondary batteries, present high risks of fire and explosion. Solid-state batteries are thus garnering attention as the next-generation batteries since they eliminate fire hazards and significantly reduce the risk of explosions. Against this background, the study aimed to analyze research trends and provide insights by examining 2,927 domestic papers related to solid-state batteries over the past decade (2013-2022). Specifically, we used topic modeling to extract major keywords associated with solid-state batteries research and to explore the network characteristics across major topics. The changes in research on solid-state batteries were analyzed in-depth by calculating topic dominance by year. The findings provide an overview of the emerging trends in domestic solid-state battery research, and might serve as a valuable reference in shaping long-term research directions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.17-20
• /
• 2016

딥러닝 기법이 발달함에 따라 텍스트에 내재된 의미 및 구문을 어떠한 벡터 공간 상에 표현하기 위한 언어 모델이 활발히 연구되어 왔다. 이를 통해 자연어 처리를 기반으로 하는 감성 분석 및 문서 분류, 기계 번역 등의 분야가 진보되었다. 그러나 대부분의 언어 모델들은 텍스트에 나타나는 단어들의 일반적인 패턴을 학습하는 것을 기반으로 하기 때문에, 문서 요약이나 스토리텔링, 의역된 문장 판별 등과 같이 보다 고도화된 자연어의 이해를 필요로 하는 연구들의 경우 주어진 텍스트의 주제 및 의미를 고려하기에 한계점이 있다. 이와 같은 한계점을 고려하기 위하여, 본 연구에서는 기존의 LSTM 모델을 변형하여 문서 주제와 해당 주제에서 단어가 가지는 문맥적인 의미를 단어 벡터 표현에 반영할 수 있는 새로운 언어 학습 모델을 제안하고, 본 제안 모델이 문서의 주제를 고려하여 문장을 자동으로 생성할 수 있음을 보이고자 한다.