A Semantic Representation Based-on Term Co-occurrence Network and Graph Kernel

Tae-Gil Noh,Seong-Bae Park,Sang-Jo Lee 한국지능시스템학회 2011 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.11 No.4

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.

The Semantics of Semantic Annotation

( Harry Bunt ) 한국언어정보학회 2007 학술대회 논문집 Vol.2007 No.-

This is a speculative paper, describing a recently started effort to give a formal semantics to semantic annotation schemes. Semantic annotations are intended to capture certain semantic information in a text, which means that it only makes sense to use semantic annotations if these have a well-defined semantics. In practice, however, semantic annotation schemes are used that lack any formal semantics. In this paper we outline how existing approaches to the annotation of temporal information, semantic roles, and reference relations can be integrated in a single XML-based format and can be given a formal semantics by translating them into second-order logic. This is argued to offer an incremental aproach to the incorporation of semantic information in natural language processing that does not suffer from the problems of ambiguity and lack of robustness that are common to traditional approaches to computational semantics.

A Semantic Representation Based-on Term Co-occurrence Network and Graph Kernel

노태길,박성배,이상조 한국지능시스템학회 2011 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.11 No.4

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.

A Semantic Representation Based-on Term Co-occurrence Network and Graph Kernel

Noh, Tae-Gil,Park, Seong-Bae,Lee, Sang-Jo Korean Institute of Intelligent Systems 2011 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.11 No.4

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.

WordNet-based Hybrid VSM for Document Classification

Luda Wang,Peng Zhang,Shouping Gao 보안공학연구지원센터 2016 International Journal of Database Theory and Appli Vol.9 No.1

Many text classifications depend on statistical term measures or synsets to implement document representation. Such document representations ignore the lexical semantic contents or relations of terms, leading to losing the distilled mutual information. This work proposed a synthetic document representation method, WordNet-based hybrid VSM, to solve the problem. This method constructed a data structure of semantic-element information to characterize lexical semantic contents, and support disambiguation of word stems. As a template, lexical semantic vector consisting of lexical semantic contents was built in the lexical semantic space of corpus, and lexical semantic relations are marked on the vector. Then, it connects with special term vector to form the eigenvector in hybrid VSM. Applying algorithm NWKNN, on text corpus Reuter-21578 and its adjusted version, the experiments show that the eigenvector performs F1 measure better than document representations based on TF-IDF.

시각 자극에 대한 희소 분포 표현 기반 형태적 시맨틱 기억 모델

강규창,배창석 한국차세대컴퓨팅학회 2020 한국차세대컴퓨팅학회 논문지 Vol.16 No.5

This paper proposes a model to remember and recall morphological semantic of input visual stimuli using SDR (sparse distributed representation). Neocortex in human brain is in charge of information processing and memory, and operation of neurons in neocortex can be modeled by sparse distributed representation. This memory model based on sparse distributed representation can be considered as memory precess and recall process separately. First, memory process means a process to convert input visual stimuli to sparse distributed representation, and in this process, morphological semantic of input visual stimuli can be preserved. Next, recall process can be considered by comparing sparse distributed representation of new input visual stimulus and remembered sparse distributed representations. Superposition of sparse distributed representation is used to measure similarities. Experimental results using 10,000 images in MNIST (Modified National Institute of Standards and Technology) data set show that the sparse distributed representation of the proposed model efficiently keeps morphological semantic of the input visual stimuli. 본 논문에서는 시각적인 자극을 희소 분포로 표현함으로써 입력 자극이 가지고 있는 형태적인 시맨틱을 기억하고 리콜하는 모델을 제안한다. 사람의 두뇌에서 대뇌 신피질은 정보 처리와 기억을 담당하며 대뇌 신피질에서 뉴런의 동작 메커니즘은 희소 분포 표현 (SDR; Sparse Distributed Representation)으로 모델링 할 수 있다. 이와 같은 희소 분포 표현 기반의 기억 모델은 입력 자극을 기억하는 과정과 유사한 기억을 리콜하는 과정으로 구분하여 고려할 수 있다. 먼저, 기억 과정은 시각 자극을 희소 분포 표현으로 변환하는 과정이며, 이 과정에서 기본적으로 입력 정보의 형태적인 시맨틱이 유지된다고 생각할 수 있다. 다음으로 이와 같이 기억된 정보와 새로운 입력 자극에 대한 희소 분포 표현들을 비교함으로써 유사한 형태적 시맨틱을 가지고 있는 기억을 리콜할 수도 있다. 본 논문에서는 리콜 과정에서 형태적 시맨틱의 유사도를 측정하기 위한 기준으로 희소 분포 표현의 중첩률을 사용한다. MNIST (Modified National Institute of Standards and Technology) 데이터를 활용한 제안 모델의 실험 결과 10,000 개의 영상을 기억에 사용하고 주어진 시각 자극에 대한 리콜 실험을 한 결과 희소 분포 표현이 시각 자극의 형태적 시맨틱을 잘 유지하고 있음을 확인하였다.

아동의 의미표상에 관한 문헌연구

한민경(Min Kyung Han) 한국언어치료학회 2015 言語治療硏究 Vol.24 No.3

Purpose: The meaning of known words stored in semantic representation in long-term memory communicates withphonological and morphological information for language processing. The purpose of this study was to review studies on semantic representation in fast mapping, word learning, aspects of quantity and quality in words, and lexical access and retrieval in language processing to explore the current trends of semantic representation studies, and to provide theoretical and clinical implications of the findings. Methods: A total of 28 articles were selected from the Journal of Speech,Language, and Hearing Research (JSLHR); Language, Speech, and Hearing Services in Schools (LSHSS); American Journal of Speech-Language Pathology (AJSLP); and American Journal of Audiology (AJA) that are published by the American Speech-Language-Hearing Association (ASHA). These were then analyzed based on current trends of studies,research tasks, and research topics. Results: Twenty-five articles among the selected 28 were published in the JSLHR.Studies with children with other disorders besides specific language disorders have emerged in the last two years, and the studies on language processing have greatly increased since 2010. In addition, the selected articles revealed that semantic deficits in children with language impairment were attributed to limited cognitive capacity and weak semantic representation. Conclusions: It is recommended that speech-language pathologists assess the various aspects of semantic deficits beyond vocabulary size in children with language impairments, leading to effective intervention

비디오 서버에서 온톨로지를 이용한 의미기반 장면 검색

정민영(Min Young Jung),박성한(Sung Han Park) 대한전자공학회 2008 電子工學會論文誌-CI (Computer and Information) Vol.45 No.5

최근 멀티미디어 정보의 양이 빠른 속도로 증가함에 따라 비디오 자료에 대한 효율적 관리는 매우 중요한 의미를 가지게 되었다. 비디오는 대용량적인 특성과 비정형적인 특성을 가지고 있어 신속하고 효율적으로 비디오 검색을 하기 위해서는 정확한 특징 정보를 추출하여 비디오 색인 구조를 구축해야 한다. 비디오 색인 구조는 전통의 데이터베이스와는 다른 모델링 방법과 검색 방법을 사용한다. 따라서 비디오 색인 구조에서 검색의 속도와 정확도를 향상시키기 위해서는 새로운 비디오 색인 구조가 필요하다. 본 논문에서는 의미적으로 비디오를 장면단위로 검색할 수 있는 비디오 온톨로지 시스템을 제안한다. 비디오 온톨로지 시스템은 장면의 내용에 대한 키워드를 구조화 시킨 장면이름 온톨로지와 장면이 가지는 특징 정보에 대한 정보를 가지는 장면 모델 온톨로지로 구성된다. 장면 이름 온톨로지는 색인된 내용에 대한 의미적 검색이 가능하도록 단어들을 트리구조로 저장된다. 그리고 장면 모델 온톨로지는 색상, 모양, 재질과 같은 저수준 정보와 객체, 이벤트 같은 고수준 정보의 의미적 차이를 극복해 줌으로써 의미기반 검색이 가능하게 해준다. To ensure access to rapidly growing video collection, video indexing is becoming more and more important. In this paper, video ontology system for retrieving a video data based on a scene unit is proposed. The proposed system creates a semantic scene as a basic unit of video retrieval, and limits a domain of retrieval through a subject of that scene. The content of semantic scene is defined using the relationship between object and event included in the key frame of shots. The semantic gap between the low level feature and the high level feature is solved through the scene ontology to ensure the semantic-based retrieval.

그림에 대한 의미론의 가능성과 의의

강선아 ( Sun Ah Kang ) 한국미학회 2010 美學 Vol.64 No.-

Semantics has been a comparatively ignored area in the discourse on pictures, presumably because, on the one hand, pictorial meaning seems to be so transparent that we can get it relatively with little effort and, on the other hand, Goodman`s influential theory of depiction preempts any possibility of proper syntax/semantics distinction with regard to pictorial representation. However, Kulvicki`s structural approach to pictorial representation provides a promising ground for syntactic identity criteria for pictures. He revises Goodman`s theory according to which syntactic and semantic density and relative repleteness jointly comprise discriminating conditions for pictorial representation. Kulvicki changes each condition to relative syntactic sensitivity, semantic richness and relative repleteness, and adds transparency condition to them. According to Kulvicki`s theory, linear perspective system is considered as a standard pictorial representation and projective invariants play an important role as an syntactically relevant properties of pictures, because syntactic identity of pictures supervenes on them. Once we acknowledge a syntax for pictures, we can proceed to the next step in which we establish formal semantics for pictures on the basis of the syntax. On this stage, Malinas seems to provide an appropriate model for formal semantics for pictures. A significant advantage of his model is that his doesn`t rely on linguistic reduction of pictorial content. According to Malinas` possible world semantics for pictures, regions and attributes of picture denote objects and attributes of scenes of possible worlds. This formula results in reducing pictorial content to visually perceptible one. This result is welcome because this reduced content can form a basic layer of pictorial meaning and consequently reveal the hierarchy of pictorial meaning. A semantics for picture may open up a road for systematic study on pictorial meaning.

EPC 네트워크의 전자물품코드(EPC) 데이타 의미표현과 해석

박대원(Dae-Won Park),권혁철(Hyuk-Chul Kwon) 한국정보과학회 2009 정보과학회논문지 : 소프트웨어 및 응용 Vol.36 No.1

Ontology is an explicit specification of concepts and relationships between concepts in an interest domain. As considered as one of typical knowledge representation methods, ontology is applied to various studies such as information extraction, information integration, information sharing, or knowledge management. In IT based industries, ontology is applied to research on information integration and sharing in order to enhance interoperability between enterprises. In supply chains or logistics, several enterprises participate as business partners to plan movements of goods, and control goods and logistics flows. A number of researches on information integration and sharing for the effective and efficient management of logistics or supply chains have been addressed. In this paper, we address an ontology as a knowledge-base for semantic-based integration of logistics information distributed in the logistics flow. Especially, we focus on developing an ontology that enables to represent and translate semantic meaning of EPC data in the EPC Network applied logistics. We present a scenario for tracing products in logistics in order to show the value of our ontology. 온톨로지는 관심 영역의 개념과 개념관계를 명시적으로 명세한 것을 말하며, 지식 표현의 대표적인 방법으로 인식되어 의미에 기반을 둔 정보의 추출, 지식 관리, 정보 공유 등 다양한 분야에서 온톨로지를 적용한 연구가 이루어지고 있다. 정보기술(IT) 기반의 경제/산업 분야에서 기업 간의 상호 협력을 위한 정보 공유 및 통합 연구에 온톨로지의 적용이 이루어지고 있다. 여러 업체가 물류 주체로 참여하며 물품의 이동, 보관, 배송 등을 계획하고 관리하는 물류 분야에서도 원활한 공급체인관리나 물류관리를 위한 물류정보의 통합과 정보공유 연구가 많이 이루어지고 있다. 최근에는 물품마다 부여한 고유의 식별코드에 의한 물품의 추적과 관리, 물류 과정의 가시성 제공 등의 요구가 발생하면서 물류 과정에 흩어져 있는 물류정보의 통합 제공 요구가 증가하고 있다. 이에 본 논문에서는 물류 과정에서 발생하는 데이타를 의미에 기반을 두고 해석하고 통합하기 위한 지식자원으로 물류 도메인 온톨로지를 제시한다. 물품을 식별하는 고유 식별코드인 전자물품코드(EPC)로 물품의 추적과 관리가 이루어지는 EPC 네트워크 기반의 물류 환경에서 발생하는 EPC 이벤트 데이타를 의미에 따라 표현하고 이벤트 데이타의 내포된 의미를 해석할 수 있는 개념과 개념관계를 표현하는 데 초점을 맞추어 온톨로지를 구성하였다. 그리고 EPC 네트워크 기반의 물류 환경에서 물품의 위치, 상태, 이동경로 등 물류 관리를 위한 정보추출 과정에서 물류 도메인 온톨로지가 이용될 수 있음을 물류 시나리오를 통해 보였다.