• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.155-159
• /
• 2018

최근 화두가 되고있는 지능형 개인 비서 시스템에서 자연어 이해(NLU) 시스템은 중요한 구성요소이다. 자연어 이해 시스템은 사용자의 발화로부터 대화의 도메인(domain), 의도(intent), 의미적 슬롯(semantic slot)을 분류하는 역할을 한다. 하지만 자연어 이해 시스템을 학습하기 위해서는 많은 양의 라벨링 된 데이터를 필요로 하며 새로운 도메인으로 시스템을 확장할 때, 새롭게 데이터 라벨링을 진행해야 하는 한계점이 존재한다. 이를 해결하기 위해 본 연구는 적대 학습 방법을 이용하여 풍부한 양으로 구성된 기존(source) 도메인의 데이터부터 적은 양으로 라벨링 된 데이터로 구성된 대상(target) 도메인을 위한 슬롯 채우기(slot filling) 모델 학습 방법을 제안한다. 실험 결과 적대 학습을 적용할 경우, 적대 학습을 적용하지 않은 경우 보다 높은 f-1 score를 나타냄을 확인하였다.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.311-314
• /
• 2007

Spoken dialog system development includes many laborious and inefficient tasks. Since there are many components such as speech recognizer, language understanding, dialog management and knowledge management in a spoken dialog system, a developer should take an effort to edit corpus and train each model separately. To reduce a cost for editting corpus and training each models, we need more systematic and efficent working environment. For the working environment, we propose DialogStudio as an spoken dialog system workbench.

• 대한음성학회지:말소리
• /
• 제42호
• /
• pp.37-46
• /
• 2001

Recently speech technologies have shown notable advancements and they now play major roles in computer-aided language learning systems. In the current paper, use of speech recognition technologies is viewed with our system for teaching English pronunciation to Japanese speakers.

• 정보처리학회논문지B
• /
• 제15B권6호
• /
• pp.595-602
• /
• 2008

각 문장 별 중점단어는 발화음성을 인식하고 그 의미를 이해하는데 도움을 준다. 발화된 음성신호로부터 중점단어를 탐색할 수 있는 방법을 찾기 위한 노력의 일환으로 실험을 통하여 문장 내에서 중점단어와 그 외의 단어들의 기본주파수의 평균과 분산, 그리고 평균 에너지를 분석해 보았다. 한국어로 된 100개의 발화문장의 음성데이터를 가지고 실험을 한 결과 중점단어는 그 외의 단어들에 비해 대부분 상대적으로 높은 기본주파수의 평균값을 나타내거나 상대적으로 높은 기본주파수의 분산 값을 나타냈다. 이 연구 결과를 이용하면 한국어의 구어문장에서 운율적 특성을 알 수 있을 뿐만 아니라, 자연어 처리를 이용한 핵심어를 추출하는 데에도 도움이 될 것이다.

• 영어어문교육
• /
• 제3호
• /
• pp.203-229
• /
• 1997

This paper is to examine a desirable and promising approach to an effective English teaching in elementary schools. Teachers' understanding English curriculum, teaching methodology, language skills-listening and speaking, and their testing of spoken communication is necessary for students' better learning in their English classes. Thus detailed explanations of English curriculum are presented, and background knowledge of major traditional teaching methods as well as recent trends is discussed. Especially, for the purpose of developing students' English communicative proficiency. classroom teaching and testing techniques of listening and speaking are also discussed with examples.

• 아동학회지
• /
• 제11권2호
• /
• pp.44-58
• /
• 1990

Literacy acquisition is a social phenomenon. Children in a literate society grow up with literacy as an integral part of their personal, familial, and social histories. Because it is language, children learn written language in ways similar to oral language. However. because it is written, the ways in which written language differs from oral language in terms of its different functions and forms affect the way in which children learn written language. Written language is likely to be more decontextualized than spoken language. The ability to use decontextualized language seems to be crucial to successful participation and progress in school. Experiences identified as contributing to preschool children's literacy development contribute to their ability to use language in a decontextualized way. Teale and Sulzby's(1986) metaphor of emergent literacy has provided a conceptual scheme for understanding the nature and process of literacy acquisition in early childhood.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제26권1호
• /
• pp.31-38
• /
• 2023

Mathematics educators have emphasized the importance of language use in mathematics education. However, previous studies have predominantly focused on the spoken language used in mathematics classrooms, which provides limited information on the written language used by mathematics teachers. The written language reflects the characteristics of the teacher community and social, cultural, and political contexts. Moreover, the written language affects teachers' instructional practices and their students' mathematics learning experiences. Therefore, this study aims to review a study conducted by Lee and Kim (2022) investigating changes in mathematics teachers' pedagogical lexicons.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2435-2438
• /
• 2003

In this paper, we propose a Korean speech understanding model using dictionary and thesaurus. The proposed model search the dictionary for the same word with in input text. If it is not in the dictionary, the proposed model search the high level words in the high level word dictionary based on the thesaurus. We compare the probability of sentence understanding model with threshold probability, and we'll get the speech understanding rate. We evaluated the performance of the sentence speech understanding system by applying twenty questions game. As the experiment results, we got sentence speech understanding accuracy of 79.8％. In this case probability of high level word is 0.9 and threshold probability is 0.38.

• Journal of Electrical Engineering and information Science
• /
• 제1권1호
• /
• pp.1-9
• /
• 1996

A key issue in spoken language processing has become the integration of speech understanding and natural language processing(NLP). This paper presents a parallel computational model for the integration of speech and NLP. The model adopts a hierarchically-structured knowledge base and memory-based parsing techniques. Processing is carried out by passing multiple markers in parallel through the knowledge base. Speech-specific problems such as insertion, deletion, and substitution have been analyzed and their parallel solutions are provided. The complete system has been implemented on the Semantic Network Array Processor(SNAP) and is operational. Results show an 80% sentence recognition rate for the Air Traffic Control domain. Moreover, a 15-fold speed-up can be obtained over an identical sequential implementation with an increasing speed advantage as the size of the knowledge base grows.

• 대한수학교육학회지:수학교육학연구
• /
• 제10권1호
• /
• pp.85-102
• /
• 2000

The concept of variables is central to mathematics teaching and learning in junior and senior high school. Understanding the concept provides the basis for the transition from arithmetic to algebra and necessary for the meaningful use of all advanced mathematics. Despite the importance of the concept, however, much has been written in the last decade concerning students' difficulties with the concept. This Thesis is based on research to investigate the hypothesis that LOGO programming will contribute to 6th grader' learning of variables. The aim of the research were to; .investigate practice on pupils' understanding of variables before the activity with a computer; .identify functions of LOGO programming in pupils' using and understanding of variable symbols, variable domain and the relationship between two variable dependent expressions during the activity using a computer; .investigate the influence of pupils' mathematical belief on understanding and using variables. The research consisted predominantly of a case study of 6 pupils' discourse and activities concerning variable during their abnormal lessons and interviews with researcher. The data collected for this study included video recordings of the pupils'work with their spoken language.