• Journal of Information Processing Systems
• /
• 제18권1호
• /
• pp.26-47
• /
• 2022

Chatbots were an important research subject in the past. A chatbot is a computer program or an artificial intelligence program that participates in a conversation via auditory or textual methods. As the research on chatbots progressed, some important issues regarding them changed over time. Therefore, it is necessary to review the technology with a focus on recent advancements and core research technologies. In this paper, we introduce five different chatbot technologies: natural language processing, pattern matching, semantic web, data mining, and context-aware computer. We also introduce the latest technology for the chatbot researchers to recognize the present situation and channelize it in the right direction.

• 중국학논총
• /
• 제71호
• /
• pp.41-59
• /
• 2021

With the progress of social economy and science and technology, network media technology has developed rapidly, China has ushered in the network information age, and the network buzzwords emerged to reflect the interaction and influence between language and society. The network buzzwords of "X+ ren "indirectly show the social psychology and value orientation of modern people with their unique structural characteristics, semantic connotation and cultural deposits, and so on. Based on this, we have conducted a multi-angle investigation on the network buzzwords "X+ ren". This paper first analyzes the structure types and syntactic functions of the lexical model of "X+ ren ", then makes a semantic analysis of the lexical model of "X+ Ren ", and finally investigates the causes and influences of the popularity of "X+ ren ". Through the investigation, we believe that "X+ ren "will continue to grow, and "X+ ren" will continue to attract the attention of the academic community.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2020년도 제32회 한글 및 한국어 정보처리 학술대회
• /
• pp.233-236
• /
• 2020

개체 연결 태스크는 문장 내에 등장하는 멘션(Mention)들을 위키피디아(Wikipedia)와 같은 지식 베이스 상의 실제 개체에 연결하는 태스크이다. 본 논문에서는 각 멘션을 시멘틱(Semantic)으로 분류하여 각 시멘틱별 추가 학습을 진행할 수 있는 Adapter Memory Network 모델을 제안한다. 이는 각 시멘틱 별 학습을 하나의 통합된 과정으로 진행하도록 하는 모델이며, 본 논문에서는 Adapter Memory Network 모델을 통해 기존 개체 연결 태스크에서 높은 성능을 보이는 NIL 멘션 탐지와 개체 연결의 통합 모델의 성능을 향상시켰음을 보인다.

• 지능정보연구
• /
• 제11권2호
• /
• pp.1-15
• /
• 2005

쇼핑몰들의 상품 정보를 효과적으로 비교할 수 있는 비교 쇼핑(comparison shopping) 시스템에서 사용자가 찾고자하는 상품에 대한 정확한 지식이 없이 검색할 경우, 불필요한 검색 결과로 인해 시스템의 효용성을 떨어지고, 사용자는 많은 시간을 소비하게 된다. 이러한 문제를 해결하기 위해서 시맨틱 웹 기반의 이미지 검색을 이용한 비교 쇼핑 시스템(Comparison Shopping Systems using Image Retrieval based on Semantic Web)을 제안한다. 제안된 시스템에서는 각 쇼핑몰들의 상품 이미지들을 온톨로지(Ontology) 기반으로 주석(annotation)처리한 후, 주석처리 된 이미지들을 통해 쇼핑몰을 구축하게 된다. 사용자는 이렇게 생성된 쇼핑몰에서 복잡한 키워드 검색을 이미지 검색으로 대체하여, 자신의 요구사항을 반영하고, 보다 정확한 검색을 할 수 있게 된다. 제안된 시스템의 성능평가를 위해 기존의 키워드 검색 기반 시스템과 단순 시맨틱 웹 기반의 비교 쇼핑 시스템의 성능을 비교 평가하였다. 그 결과, 시맨틱 웹 기반의 이미지 검색을 이용한 비교쇼핑 시스템이 키워드 검색기반과 시맨틱 웹 기반의 비교 쇼핑 시스템보다 평균적으로 50%, 20% 향상된 성능을 보였다.

• 한국환경복원기술학회지
• /
• 제21권3호
• /
• pp.67-81
• /
• 2018

We tried to analyze qualitatively a total of 110 the research papers which were related domestic ecological restoration technologies about 15 years through semantic network analysis in social network analysis. In order to understand the research trends of ecological restoration technologies, we analyzed the degree centrality and betweenness centrality of the Stream/Wetland, Slope, Soil/Others fields selected as Word Cloud. As a result, ecological restoration technologies have been changed. They were focused on the restoration of species or their habitats in the past. However, they have been evolved into the detailed systems to respond in unpredictable natural disasters and climate change, high-resolution image implementation technology to accurately grasp the practical environment and methods related to environmental restoration for human in urban ecosystem. In the future, investment and technology for the ecosystem restoration field will be continuously demanded for the symbiosis of human beings and species in the damaged ecosystem. Therefore, the research trend of ecological restoration technologies should be provided as reliable guidelines when decision makers establish the policy direction or when researchers select their subjects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 1998년도 Language, Information and Computation = Selected Papers from the 12th Pacific Asia Conference on Language, Information and Computation, Singapore
• /
• pp.340-347
• /
• 1998

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2001년도 Bulletin of The 5th Asian Design Conference International Symposium on Design Science
• /
• pp.30.1-30
• /
• 2001

• 지식정보인프라
• /
• 통권6호
• /
• pp.36-41
• /
• 2001

SW이란 컴퓨터가 스스로 웹상의 자료를 처리할 수 있도록 하기 위한 차세대 지능형 웹을 말한다. 현재 웹을 무시하고 전혀 새로운 웹을 만들고자 하는 시도가 아니고 현재까지 검증된 기술에 추가적인 기능을 부가하여 추론 등의 기능을 구현하고자 하는 시도이다.