• 한국실내디자인학회논문집
• /
• 제18권5호
• /
• pp.71-79
• /
• 2009

This research understands semantics-system in contemporary space design as a poetic form. It provides that the possibility of various interpretation of space and makes to escape from insipid formal logic of compulsion uniform meaning. In order to unfold this argument, poetic semantics system has to be revealed using conversion of articulation factors in text of space(semantics and syntax). First of all, after setting up the articulation system of space language, we have to understand the conversion of articulation factors that generate a new grammar breaking up the rule of old syntax. And the various expression of form in Contemporary Space design focuses on a poetic expression, that is, the abstraction system fused by space factors(conversion of articulation system). In this method of research to recognize the subject of space in architecture, the importance of interpretation has to be highlighted, as the importance of language is emphasized that intermediates between object and interpretation. The reason to recognize Contemporary space design as a text is that it is a gathering of symbol as a object of interpretation and a mediator. The important issue of this study is to research how and what to transmit by poetic semantics system in contemporary space design. It brings about a poetic problem what it intends to becomes(the problem of meaning operation) in a narrow sense and a interpretational problem what it intends to do(the problem of communication). When we define interpretation the technique of defining a text, it involves the premise of inevitableness of multiple understanding, or the possibility to Interpret variously. In the end the ambiguity of poetic language and the infinity of moaning process as the moaning expansion system in contemporary space design is the flexible measure to solve the self-criticism.

• 한국정보시스템학회지:정보시스템연구
• /
• 제21권3호
• /
• pp.137-161
• /
• 2012

The increasing interest in big data analysis using various data mining techniques indicates that many commercial data mining tools now need to be equipped with fundamental text analysis modules. The most essential prerequisite for accurate analysis of text documents is an understanding of the exact semantics of each term in a document. The main difficulties in understanding the exact semantics of terms are mainly attributable to homonym and synonym problems, which is a traditional problem in the natural language processing field. Some major text mining tools provide a thesaurus to solve these problems, but a thesaurus cannot be used to resolve complex synonym problems. Furthermore, the use of a thesaurus is irrelevant to the issue of homonym problems and hence cannot solve them. In this paper, we propose a semantic text mining methodology that uses ontologies to improve the quality of text mining results by resolving the semantic ambiguity caused by homonym and synonym problems. We evaluate the practical applicability of the proposed methodology by performing a classification analysis to predict customer churn using real transactional data and Q&A articles from the "S" online shopping mall in Korea. The experiments revealed that the prediction model produced by our proposed semantic text mining method outperformed the model produced by traditional text mining in terms of prediction accuracy such as the response, captured response, and lift.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.13-28
• /
• 2007

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.

• 한국문헌정보학회지
• /
• 제56권1호
• /
• pp.95-117
• /
• 2022

본 연구는 시선 및 뇌파 정보를 이용하여 오디오-비주얼(audio-visual, AV) 시맨틱스 기반의 동영상 요약 방법들을 개발하고 평가해 보았다. 이를 위해서 27명의 대학생들을 대상으로 시선추적과 뇌파 실험을 수행하였다. 평가 결과, 뇌파와 동공크기 데이터를 함께 사용한 방법의 평균 재현율(0.73)이 뇌파 또는 동공크기 데이터만을 사용한 방법의 평균 재현율(뇌파: 0.50, 동공크기: 0.68)보다 높게 나타났다. 또한 AV 시맨틱스 기반의 개인화된 동영상 요약의 평균 재현율(0.57)이 AV 시맨틱스 기반의 일반적인 동영상 요약의 평균 재현율(0.69)보다 낮게 나타난 원인들을 분석하였다. 끝으로, AV 시맨틱스 기반 동영상 요약 방법과 텍스트 시맨틱스 기반 동영상 요약 방법 간의 차이 및 특성도 비교분석해 보았다.

• ETRI Journal
• /
• 제46권1호
• /
• pp.35-47
• /
• 2024

This study introduces CR-M-SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding-based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost-effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR-M-SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high-recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• 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.

• 한국실내디자인학회논문집
• /
• 제16권4호
• /
• pp.31-38
• /
• 2007

This study is interested in how philological interpretation of a space text were patterned so as to give the text structural cohesion. A similar philological motivation incorporates some of the notions of generative grammar. Interpretation is the process of recovering the cultural meanings expressed in discourse by analysing the linguistic structures in the light of their interactional and wider social contexts. Viewed in this light, the process of this study is illustrated as follows: At first, this research contains basic concepts of signification of text and context, and theories of spacial text and context of typological structure in terms of Ricoeur's structural Hermeneutics. Secondly, it concretize a logic that traditional space context is inserted in organized attribute like emotion, spirit, nature as character of contemporary space text through typological structure. Finally, from aspect of designation theory among interpretive semantics, it shows that korean contemporary space design is incorporated with typological structure of korean traditional palace spacial context homologically through the case study of I-Hotel space design. Through this process, this study suggest that positivistic interpretation methodology by designation of text is logical thinking of Korean traditional space design.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1891-1908
• /
• 2021

Cyber deception defense mitigates Advanced Persistent Threats (APTs) with deploying deceptive entities, such as the Honeyfile. The Honeyfile distracts attackers from valuable digital documents and attracts unauthorized access by deliberately exposing fake content. The effectiveness of distraction and trap lies in the enticement of fake content. However, existing studies on the Honeyfile focus less on this perspective. In this work, we seek to improve the enticement of fake text content through enhancing its readability, indistinguishability, and believability. Hence, an enticing deceptive-content generator, EDGE, is presented. The EDGE is constructed with three steps: extracting key concepts with a semantics-aware K-means clustering algorithm, searching for candidate deceptive concepts within the Word2Vec model, and generating deceptive text content under the Integrated Readability Index (IR). Furthermore, the readability and believability performance analyses are undertaken. The experimental results show that EDGE generates indistinguishable deceptive text content without decreasing readability. In all, EDGE proves effective to generate enticing deceptive text content as deception defense against APTs.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.401-403
• /
• 2019

In this paper, we propose a generative adversarial networks (GAN) based text-to-image generating method. In many natural language processing tasks, which word expressions are determined by their term frequency -inverse document frequency scores. Word2Vec is a type of neural network model that, in the case of an unlabeled corpus, produces a vector that expresses semantics for words in the corpus and an image is generated by GAN training according to the obtained vector. Thanks to the understanding of the word we can generate higher and more realistic images. Our GAN structure is based on deep convolution neural networks and pixel recurrent neural networks. Comparing the generated image with the real image, we get about 88% similarity on the Oxford-102 flowers dataset.

• 한국정보처리학회논문지
• /
• 제6권6호
• /
• pp.1447-1457
• /
• 1999

최근 제안된 시각 객체 질의어(VOQL)는 시각 질의어로 스키마 정보가 시각적으로 질의 표현에 포함되므로 복잡한 구조의 데이터에 대한 질의를 효과적으로 표현할 수 있는 객체 지향 데이터베이스 질의어이다. VOQL은 귀납적으로 정의된 시맨턱을 갖는 그래프 기반 언어로 다양한 텍스트 경로식들을 그래프로 간결하게 표현 할 뿐 아니라 복잡한 경로식의 시맨틱을 명확하게 전달한다. 그러나 기존의 VOQL은 모든 속성을 다중 값으로 가정하고 있고, 객체변수의 바인딩 개념을 시각화하고 있지 못하고 있다. 이로 인해 VOQL 질의문의 표현이 직관적이지 못할 뿐 아니라 이론적 확장이 쉽지 않다. 본 논문에서는 이러한 문제를 해결하도록 VOQL을 개선하고 한다. 단일 값과 다중 값을 갖는 속성의 결과를 각각 시각 요소와 서브 블랍을 통해 시각화하고, 시각변수를 도입하여 객체 변수의 바인딩을 명시화하여 질의문의 시맨틱을 직관적이고, 명확하게 하고 있다.