• 영어어문교육
• /
• 제13권1호
• /
• pp.261-282
• /
• 2007

The purpose of this study is to investigate American traditional values and American culture in English education. The understanding of American culture in English education requires the analysis of world changes in the global age. The history of American English, the formation of American society, and the background of natural environment are described in relation to the traditional American values of the earliest settlers, such as multi-culture, individual freedom, frontier heritage in the West, equality of opportunity and wealth and material abundance. Hence the case studies of students' project presentations on the American culture in English education exemplify the reflection of American traditional values in the current American life and society. It is concluded that project-based method with regard to cultural studies in English education reveals very positive learning effects by driving students' interests and active participation through the student-centered, creative, and cooperative project presentations.

• 인지과학
• /
• 제3권1호
• /
• pp.41-60
• /
• 1991

대부분의 PC 사용자들은 늘 사용하는 몇 가지 명령만으로 컴퓨터를 조작하고 있다. 그러나 DOS명령 대신 한글 문장으로 컴퓨터를 조작한다면, 최적의 명령어를 생성해낼수 있을뿐 아니라 사용자에게 융통성을 제공할 수 있다. 이를 위하여 본 논문에서는 자연어로 입력되는 한글 문장을 형태소 분석, 구문분석, 의미분석, 개념분석을 통해 일련의 DOS명령으로 변환하는 방법을 연구하였다. 형태소 분석에서는 Tabular Parsing 이 이용되고, 구문 분석과 의미분석에서는 격문법이 이용된다. 문자의 의미는 개념망으로 표현되고 이로부터 DOS 명령어가 생성된다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.42.3-42
• /
• 2002

Fuzzy Neural Network (FNN) is a compulsory element in a voice-controlled machine due to its inherent capability of interpreting imprecise natural language commands. To control such a machine, user's perception of imprecise words is very important because the words' meaning is highly subjective. This paper presents a voice based controller centered on an adaptable FNN to capture the user's perception of imprecise words. Conversational interface of the machine facilitates the learning through interaction. The system consists of a dialog manager (DM), the conversational interface, a Knowledge base, which absorbs user's perception and acts as a replica of human understanding of imprecise words,...

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.330-333
• /
• 2007

This paper presents a dialogue interface using the dialogue management system as a method for controlling home appliances in Home Network Services. In order to realize this type of dialogue interface, we annotated 96,000 utterance pair sized dialogue set and developed an example-based dialogue system. This paper introduces the automatic error correction module for the SMS-styled sentence. With this module we increase the accuracy of NLU(Natural Language Understanding) module. Our NLU module shows an accuracy of 86.2%, which is an improvement of 5.25% over than the baseline. The task completeness of the proposed SMS dialogue interface was 82%.

• 대한조선학회지
• /
• 제25권1호
• /
• pp.56-62
• /
• 1988

Artificial Intelligence(AI) is that branch of computer science that deals with designing computer system that exhibit some of the characteristics associated with intelligence on human behaviors such as, understanding natural language, reasoning, solving problems, robotics and so on. The most developed component of artificial intelligence today is probably the expert system. An expert system is defined as a computer program that embodies organized knowledge concerning some specific domain of human expertise and programmed to perform convincingly as an advisory consultant in the given domain with self-explanation of reasoning on demand. This paper describes general concept of artificial intelligence and expert system and investigates applicability of expert system to ship design.

• 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.

• Journal of information and communication convergence engineering
• /
• 제17권3호
• /
• pp.191-197
• /
• 2019

Morphological analysis is used for searching sentences and understanding context. As most morpheme analysis methods are based on predefined dictionaries, the problem of a target word not being registered in the given morpheme dictionary, the so-called unregistered word problem, can be a major cause of reduced performance. The current practical solution of such unregistered word problem is to add them by hand-write into the given dictionary. This method is a limitation that restricts the scalability and expandability of dictionaries. In order to overcome this limitation, we propose a novel method to automatically expand a dictionary by means of use-case analysis, which checks the validity of the unregistered word by exploring the use-cases through web crawling. The results show that the proposed method is a feasible one in terms of the accuracy of the validation process, the expandability of the dictionary and, after registration, the fast extraction time of morphemes.

• International journal of advanced smart convergence
• /
• 제10권2호
• /
• pp.130-137
• /
• 2021

In the current software project, it is still very difficult to extract and define clear requirements in the requirement engineering. Informal requirements documents based on natural language can be interpreted in different meanings depending on the degree of understanding or maturity level of the requirements analyst. Also, Furthermore, as the project progresses, requirements continue to change from the customer. This change in requirements is a catastrophic failure from a management perspective in software projects. In the situation of frequent requirements changes, a current issue of requirements engineering area is how to make clear requirements with unclear and ambigousrequirements. To solve this problem, we propose to extract and redefine clear requirements by incorporating Design Thinking methodologies into requirements engineering. We expect to have higher possibilities to improve software quality by redefining requirements that are ambiously and unclearly defined.

• International journal of advanced smart convergence
• /
• 제12권1호
• /
• pp.120-129
• /
• 2023

Perspective taking, one's knowledge of their own mental and emotional states and inferences about others' mental and emotional states, is an important higher order cognitive skill required in successful writing. However, there has not been much research on the identification and examiantion of the psychometrics of perspective taking. To fill in this gap, I reviewed the psychological and cognitive frameworks of perspective taking including theory of mind, audience awareness, development of epistemological understanding, and argumentation schema. I also reviewed various methods of examining the psychometric properties of perspective taking in written composition, including both manual and computational approaches. The review of literature yielded suggestions on the development of manual coding scheme for perspective taking as well as the selection of indexes to draw from natural language processing tools. Challenges and affordances of combining the manual and computational approach are discussed along with future research directions to advance the field of psycholinguistics.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.1116-1119
• /
• 2021

2018 년 Google 사의 사전 학습된 언어 인공지능 BERT 를 기점으로, 자연어 처리 학계는 주요 구조를 유지한 채 경쟁적으로 모델을 대형화하는 방향으로 발전했다. 그 결과, 오늘날 자연어 인공지능은 거대 사기업과 그에 준하는 컴퓨팅 자원을 소유한 연구 단체만의 전유물이 되었다. 본 논문에서는 다층 퍼셉트론을 병렬적으로 배열해 자연어 인공지능을 제작하는 기법의 모델을 제안하고, 이를 적용한'조건부 게이트 다층 퍼셉트론 모델(SG-MLP)'을 구현하고 그 결과를 비교 관찰하였다. SG-MLP 는 BERT 의 20%에 해당하는 사전 학습량만으로 다수의 지표에서 그것과 준하는 성능을 보였고, 동일한 과제에 대해 더 적은 연산 비용을 소요한다.