• 한국어학
• /
• 제48권
• /
• pp.223-268
• /
• 2010

The purpose of this paper is to build a semantic networks of the 'cooking class' verb (based on 'CoreNet' of KAIST). This proceedings needs to adjust the concept classification. Then sub-categories of [Cooking] and [Foodstuff] hierarchy of CoreNet was adjusted for the construction of verb semantic networks. For the building a semantic networks, each meaning of 'Cooking verbs' of Korean has to be analyzed. This paper focused on the Korean 'heating' verbs and 'non-heating'verbs. Case frame structure and argument information were inserted for the describing verb information. This paper use a Propege 3.3 as a tool for building "cooking verb" semantic networks. Each verb and noun was inserted into it's class, and connected by property relation marker 'HasThemeAs', 'IsMaterialOf'.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.321-329
• /
• 2007

This paper reports on the application of network analysis approaches to investigate the characteristics of graph representations of Japanese word associations. Two semantic networks are constructed from two separate Japanese word association databases. The basic statistical features of the networks indicate that they have scale-free and small-world properties and that they exhibit hierarchical organization. A graph clustering method is also applied to the networks with the objective of generating hierarchical structures within the semantic networks. The method is shown to be an efficient tool for analyzing large-scale structures within corpora. As a utilization of the network clustering results, we briefly introduce two web-based applications: the first is a search system that highlights various possible relations between words according to association type, while the second is to present the hierarchical architecture of a semantic network. The systems realize dynamic representations of network structures based on the relationships between words and concepts.

• Journal of Information Technology Applications and Management
• /
• 제9권2호
• /
• pp.71-80
• /
• 2002

Automatic language translation has greatly advanced due to the increased user needs and Information retrieval in WWW. This paper utilizes the integrated knowledge bases of noun and verb networks for automatic translation of ambiguous words in the Korean sentences, through the selectional restriction relation in the sentences. And this paper presents the method to verify validity of Korean noun semantic networks that are used for the construction of the selectional restriction relation by applying the networks to the syntactic and semantic properties Integration of Korean Noun Networks into the SENKOV system will provide the accurate and efficient knowledge bases for the semantic analysis of Korean NLP.

• 지능정보연구
• /
• 제10권2호
• /
• pp.1-13
• /
• 2004

상품검색은 고객들이 전자상거래의 접촉을 시작하는 인터페이스로서 매우 중요한 프로세스이다. 또한 전자상거래는 고객들에게 검색 시 쉽게 접근할 수 있는 프로세스를 제공하여야 한다. 특히 World Wide Web에서 상품정보는 광범위한 고객들이 신속하게 팽창하는 정보를 추적하기 위해서 통합과 표준화가 이뤄져야 한다. 상품 카탈로그(catalogue)에 대한 국제 표준화가 다양한 분야와 업종에서 구축되어져 왔는데, 요즈음은 UNSPSC((Universal Standard Products and Services Classification) 코드로의 수렴에 대한 논의가 활발해지고 있다. 이 표준을 채택하여 이 논문은 다국어상품검색 에이전트의 아키텍쳐(architecture)를 설계한다. 이 아키텍쳐는 중앙등록기 모델의 상품 카탈로그 관리를 기반으로 하여 분산처리의 update프로세스를 채택한다. 또한 이 아키텍쳐는 구매자 관점과 공급자 관점을 모두 고려한다. 상품정보의 일관성과 버전 관리는 UNSPSC코드 시스템에 의하여 제어된다. 고객이 사용하기 편리하도록 표준화에 포함되어져 있지 않은 상품명과 다국어 상품명은 Semantic Network, 시소러스(thesaurus)와 Semantic Web의 상품명 온톨로지 등을 활용하여 해결한다. 이를 위한 알고리즘들을 설계하고 또한 구현한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3942-3961
• /
• 2019

Recently, the models of deep super-resolution networks can successfully learn the non-linear mapping from the low-resolution inputs to high-resolution outputs. However, for large scaling factors, this approach has difficulties in learning the relation of low-resolution to high-resolution images, which lead to the poor restoration. In this paper, we propose Stage Generative Adversarial Networks (Stage-GAN) with semantic maps for image super-resolution (SR) in large scaling factors. We decompose the task of image super-resolution into a novel semantic map based reconstruction and refinement process. In the initial stage, the semantic maps based on the given low-resolution images can be generated by Stage-0 GAN. In the next stage, the generated semantic maps from Stage-0 and corresponding low-resolution images can be used to yield high-resolution images by Stage-1 GAN. In order to remove the reconstruction artifacts and blurs for high-resolution images, Stage-2 GAN based post-processing module is proposed in the last stage, which can reconstruct high-resolution images with photo-realistic details. Extensive experiments and comparisons with other SR methods demonstrate that our proposed method can restore photo-realistic images with visual improvements. For scale factor ${\times}8$, our method performs favorably against other methods in terms of gradients similarity.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제16권6호
• /
• pp.727-731
• /
• 2010

최근 모바일 기기의 다양한 센서들을 통하여 데이타를 수집하여 개인의 삶을 기록하는 연구들이 진행 중이다. 효율적인 모바일 라이프로그의 저장과 탐색을 위해 연관 검색이 가능한 모바일 라이프로그 시맨틱 네트워크가 제안되었다. 기존의 시맨틱 네트워크 상의 검색은 텍스트 기반으로 관계를 바탕으로 하는 사용자의 능동적인 연관 검색에 한계가 있었다. 본 논문에서는 모바일 라이프로그의 연관 검색을 위해 검색 과정과 결과를 시각화된 네트워크로 데이타간의 관계를 보여주는 선택 연관 검색과 키워드 연관 검색을 제안한다. 복잡한 시맨틱 네트워크에 대해서 사용자의 이해도를 높이기 위해 의미 추상화를 적용하였다. 실제 모바일 라이프로그 시맨틱 네트워크 데이타를 바탕으로 질의를 해결하는 과정을 기존 연구에서 보였던 텍스트 기반 연관 검색 방법과 비교하고 사용성 평가를 시행함으로 유용성을 입증하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1807-1824
• /
• 2015

As the technologies advance, mobile peer-to-peer (MP2P) networks or systems become one of the major ways to share resources and information. On such a system, the information retrieval (IR), including the development of scalable infrastructures for indexing, becomes more complicated due to a huge increase on the amount of information and rapid information change. To keep the systems on MP2P networks more reliable and consistent, the index structures need to be updated frequently. For a semantic IR system, the index structure is even more complicated than a classic IR system and generally has higher update cost. The most well-known indexing technique used in semantic IR systems is Latent Semantic Indexing (LSI), of which the index structure is generated by singular value decomposition (SVD). Although LSI performs well, updating the index structure is not easy and time consuming. In an MP2P environment, which is fully distributed and dynamic, the update becomes more challenging. In this work, we consider how to update the sematic index generated by LSI and keep the index consistent in the whole MP2P network. The proposed Concept Space Update (CSU) protocol, based on distributed 2-Phase locking strategy, can effectively achieve the objectives in terms of two measurements: coverage speed and update cost. Using the proposed effective synchronization mechanism with the efficient updates on the SVD, re-computing the whole index on the P2P overlay can be avoided and the consistency can be achieved. Simulated experiments are also performed to validate our analysis on the proposed CSU protocol. The experimental results indicate that CSU is effective on updating the concept space with LSI/SVD index structure in MP2P semantic IR systems.

• Journal of Multimedia Information System
• /
• 제4권3호
• /
• pp.123-144
• /
• 2017

Personalized media includes user-targeted and user-generated content (UGC) exchanged through social media and interactive applications. The increased consumption of UGC presents challenges and opportunities to multimedia information systems. We work towards modeling a deep structure for content networks. To gain insights, a hybrid practice with Media Framework (MF) is presented for network creation of personalized media, which leverages the authoring methodology with user-generated semantics. The system's vertical integration allows users to audition their personalized media networks in the context of a global system network. A navigation scheme with dynamic GUI shifts the interaction paradigm for content query and sharing. MF adopts a multimodal architecture anticipating emerging use cases and genres. To model diversification of platforms, information processing is robust across multiple technology configurations. Physical and virtual networks are integrated with distributed services and transactions, IoT, and semantic networks representing media content. MF applies spatiotemporal and semantic signal processing to differentiate action responsiveness and information responsiveness. The extension of multimedia information processing into authoring enables generating interactive and impermanent media on computationally enabled devices. The outcome of this integrated approach with presented methodologies demonstrates a paradigmatic shift of the concept of UGC as personalized media network, which is dynamical and evolvable.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권4호
• /
• pp.238-246
• /
• 2011

This paper proposes a new semantic representation and its associated similarity measure. The representation expresses textual context observed in a context of a certain term as a network where nodes are terms and edges are the number of cooccurrences between connected terms. To compare terms represented in networks, a graph kernel is adopted as a similarity measure. The proposed representation has two notable merits compared with previous semantic representations. First, it can process polysemous words in a better way than a vector representation. A network of a polysemous term is regarded as a combination of sub-networks that represent senses and the appropriate sub-network is identified by context before compared by the kernel. Second, the representation permits not only words but also senses or contexts to be represented directly from corresponding set of terms. The validity of the representation and its similarity measure is evaluated with two tasks: synonym test and unsupervised word sense disambiguation. The method performed well and could compete with the state-of-the-art unsupervised methods.