• Title/Summary/Keyword: 언어평가

Search Result 1,675, Processing Time 0.027 seconds

Multilingual Story Link Detection based on Properties of Event Terms (사건 어휘의 특성을 반영한 다국어 사건 연결 탐색)

  • Lee Kyung-Soon
    • The KIPS Transactions:PartB
    • /
    • v.12B no.1 s.97
    • /
    • pp.81-90
    • /
    • 2005
  • In this paper, we propose a novel approach which models multilingual story link detection by adapting the features such as timelines and multilingual spaces as weighting components to give distinctive weights to terms related to events. On timelines term significance is calculated by comparing term distribution of the documents on that day with that on the total document collection reported, and used to represent the document vectors on that day. Since two languages can provide more information than one language, term significance is measured on each language space and used to refer the other language space as a bridge on multilingual spaces. Evaluating the method on Korean and Japanese news articles, our method achieved $14.3{\%}\;and\;16.7{\%}$ improvement for mono- and multi-lingual story pairs, and for multilingual story pairs, respectively. By measuring the space density, the proposed weighting components are verified with a high density of the intra-event stories and a low density of the inter-events stories. This result indicates that the proposed method is helpful for multilingual story link detection.

Action Research to Improve the Curriculum for Early Childhood Language Education Based on Design Thinking for Prospective Kindergarten Teachers (예비유아교사를 위한 디자인씽킹 중심의 유아언어교육 교과목 개선을 위한 실행연구)

  • Bae, Jee-Hyun
    • The Journal of the Korea Contents Association
    • /
    • v.21 no.12
    • /
    • pp.119-131
    • /
    • 2021
  • The purpose of this study is to improve the curriculum of major subjects by constructing and applying design thinking centered 'early childhood language education' for prospective kindergarten teachers, and to cultivate their teaching ability in the classroom. As a result of the study, it is as follows. First, in the improvement of 'early childhood language education' subjects centered on design thinking, the "plan" stage recognizes the problem of interest in language education and the execution of language areas. In the "action" step, they created a interesting stationery for plays that can be actively expressed for young children who are hard to write. In the "re-action after reflection" steps, they have developed creative writing based on the diverse experience of the who have been working on a kindergarten field practice, Second, The meaning of the implementation for the major classes based on the design thinking is listening to young children than given practice, and self-reflection and growth through sympathy and cooperation. The implications of this study are needed to change the various major classes and the experience of problem solving is that it is also helpful for the autonomy and expertise of prospective kindergarten teachers.

The perceptual judgment of sound prolongation: Equal-appearing interval and direct magnitude estimation (연장음 길이에 따른 비유창성 정도 평가: 등간척도와 직접크기평정 비교 연구)

  • Jin Park;Hwajung Cha;Sejin Bae
    • Phonetics and Speech Sciences
    • /
    • v.15 no.3
    • /
    • pp.59-67
    • /
    • 2023
  • This study aimed to propose an appropriate evaluation method for the perceived level of speech disfluency based on sound prolongation (i.e., increased duration of segments). To this end, 34 Korean-speaking adults (9 males, 25 females, average age: 32.9 yrs.) participated as raters in this study. The participants listened to sentences containing a total of 25 stimuli with the Korean voiceless fricative /s/ extended by 80-ms increments up to 2,000 ms (i.e., 285 ms, 365 ms., ..., 2,125 ms, 2,205 ms), and evaluated them using an equal-appearing interval scale (EAI, 1-7 points, where 1 represents "normal" and 7 represents "severe"). Subsequently, based on the interval-scale results, the sentence stimuli with the prolonged voiceless fricative corresponding to the mild-to-moderate level (rated as 4 points) were selected as the reference modulus for direct magnitude estimation (DME). After scatter plots were created for the two evaluation results, the relationship between the two measured mean values was analyzed using a curve estimation method for the observed data with the highest R2-value to determine whether a linear or curvilinear approximation fit the data better. A curvilinear relationship between the two evaluation results was indicated, suggesting that DME is a more appropriate evaluation method than the EAI scale for assessing the perceived level of disfluency based on sound prolongation.

Saesark: A Korean Object-Oriented Programming Language for Beginners (새싹: 초보자를 위한 한글 객체 지향 프로그래밍 언어)

  • Cheon, Junseok;Woo, Gyun
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.3
    • /
    • pp.288-295
    • /
    • 2016
  • As the computer becomes pervasive in everyday life, the programming arises as an essential technique. To support the education of programming, Republic of Korea has launched a plan to develop the official courses of programming by 2018. However, the programming education in Korea tends to be difficult and the students easily lose their concentration since most of programming languages are based on English. This paper proposes a Korean programming language called Saesark to promote the effective programming education for Korean students. Saesark has been developed based on Java, which supports the object-oriented programming and the lambda expressions. In order to evaluate the educational suitability of Saesark, we compared it with other Korean programming languages in three respects: syntactic features, IDE support, and error messages in Korean. According to the comparison, Saesark is revealed more suitable than other languages. Specifically, the IDE features and the error messages in Korean are expected to be mostly valuable in educating novice programmers.

Analysis of Teacher's Verbal Interactions and Problem Solving Strategies in Young Children's Environmental Education Using Language Network Analysis Methods (언어네트워크 분석방법을 활용한 유아환경교육에서 교사의 언어적 상호작용과 문제해결전략 분석)

  • Choi, Yoon-Ji
    • Journal of Convergence for Information Technology
    • /
    • v.11 no.3
    • /
    • pp.147-158
    • /
    • 2021
  • The purpose of this study is to perform of composition of young children teacher's verbal interactions and problem solving strategies by semantic network analysis. The data was collected the narrative of teacher in young children's environmental education. Additionally, this study used categories as a unit of analysis in order to find out structural characteristics. The results of this study were as follows. First, teacher's verbal interactions, providing information was the most cental, high influence appeared along with integration. Second, teacher's problem solving strategies, suggestion was the most cental, high influence appeared along with divergent thinking. Third, teacher's verbal interactions and problem solving strategies, suggestion was the most cental, providing information and divergent thinking appeared a strong connection. Besides, suggestion and decision were mediated by concern of problem, assessment appeared connection. Through these results from this study it is suggested that in order to interact and support problem solving process in young children's environmental education, teacher education to respond and understand contextually with young children is necessary.

The Vocabulary Recognition Optimize using Acoustic and Lexical Search (음향학적 및 언어적 탐색을 이용한 어휘 인식 최적화)

  • Ahn, Chan-Shik;Oh, Sang-Yeob
    • Journal of Korea Multimedia Society
    • /
    • v.13 no.4
    • /
    • pp.496-503
    • /
    • 2010
  • Speech recognition system is developed of standalone, In case of a mobile terminal using that low recognition rate represent because of limitation of memory size and audio compression. This study suggest vocabulary recognition highest performance improvement system for separate acoustic search and lexical search. Acoustic search is carry out in mobile terminal, lexical search is carry out in server processing system. feature vector of speech signal extract using GMM a phoneme execution, recognition a phoneme list transmission server using Lexical Tree Search algorithm lexical search recognition execution. System performance as a result of represent vocabulary dependence recognition rate of 98.01%, vocabulary independence recognition rate of 97.71%, represent recognition speed of 1.58 second.

French-Korean Computer-Assisted Translation Workbench, TransFranCo (불-한 전문분야 기계보조번역 워크벤치 TransFranCo)

  • Jeong, Hwi-Woong;Lim, Yong-Seok;Yoon, Ae-Sun
    • Proceedings of the Korean Society for Cognitive Science Conference
    • /
    • 2005.05a
    • /
    • pp.255-260
    • /
    • 2005
  • 번역 메모리(Translation Memory)는 오늘날 기계번역에 있어 통계기반 접근법이나 형태-통사적 접근법 모두에 있어 가장 중요한 요소로 평가되고 있다. 그러나 번역 메모리는 언어의 자질 및 각 용례를 통합적으로 관리해야 하며, 이를 기계가 자동으로 처리해주어야 하는 어려움이 있다. 최근에는 이러한 문제점을 해결하기 위해 다국적 기업을 중심으로 기계보조번역(Computer Aided Translation) 환경에 대한 연구가 활발히 이루어지고 있으나, 언어적인 특성 보다는 번역 메모리의 저장/대치적 측면에서 주요 연구가 이루어지고 있다. 이 논문에서는 번역 메모리 정보가 보다 높은 재사용성을 보이기 위해서는 다양한 언어자질값을 담을 수 있어야 한다고 보고, 이를 효율적으로 관리/구축할 수 있는 기계보조번역 워크벤치의 framework을 제시한다. 언어분석을 위한 대상언어로는 교역 및 기술 측면에서 영어, 일어, 중국어 다음으로 영향력이 높은 불어를 채택하며, 기존 기계보조번역 방식에 대한 고찰을 통해 개선된 번역 메모리 관리, 자동분석/번역 모듈 및 협업(collaboration) 방안에 대해 소개하고, 향후 발전방향에 대해 논의한다.

  • PDF

The Development and Evaluation of Educational Hangul Programming Language 'HanScript' (교육용 한글 프로그래밍 언어 'HanScript'의 적용)

  • Jeong, Young-Sik
    • The Journal of Korean Association of Computer Education
    • /
    • v.7 no.3
    • /
    • pp.15-22
    • /
    • 2004
  • This study developed HanScript, which is an educational Hangul programming language, in order to make programs easily and conveniently and applied it to the school fields. To evaluate HanScript, additionally, the researcher divided the properties of educational programming languages into easiness to read, easiness to write and easiness to debug and, based on them, compared HanScript with Visual Basic. According to the result, HanScript was expressed in Korean language style, so was easier to read and debug than Visual Basic. But it was not different from Visual Basic in debugging. Due to fewer libraries compared to Visual Basic, however, it was difficult to implement complex functions using HanScript. In addition, HanScript did not include an editor to edit source codes. Thus, if HanScript is equipped with rich libraries, detailed debugging information and an editor for source code edition, it will be a useful educational programming language.

  • PDF

Measuring Sentence Similarity using Morpheme Embedding Model and GRU Encoder for Question and Answering System (질의응답 시스템에서 형태소임베딩 모델과 GRU 인코더를 이용한 문장유사도 측정)

  • Lee, DongKeon;Oh, KyoJoong;Choi, Ho-Jin;Heo, Jeong
    • Annual Conference on Human and Language Technology
    • /
    • 2016.10a
    • /
    • pp.128-133
    • /
    • 2016
  • 문장유사도 분석은 문서 평가 자동화에 활용될 수 있는 중요한 기술이다. 최근 순환신경망을 이용한 인코더-디코더 언어 모델이 기계학습 분야에서 괄목할만한 성과를 거두고 있다. 본 논문에서는 한국어 형태 소임베딩 모델과 GRU(Gated Recurrent Unit)기반의 인코더를 제시하고, 이를 이용하여 언어모델을 한국어 위키피디아 말뭉치로부터 학습하고, 한국어 질의응답 시스템에서 질문에 대한 정답을 유추 할 수 있는 증거문장을 찾을 수 있도록 문장유사도를 측정하는 방법을 제시한다. 본 논문에 제시된 형태소임베딩 모델과 GRU 기반의 인코딩 모델을 이용하여 문장유사도 측정에 있어서, 기존 글자임베딩 방법에 비해 개선된 결과를 얻을 수 있었으며, 질의응답 시스템에서도 유용하게 활용될 수 있음을 알 수 있었다.

  • PDF

Dependency parsing applying reinforced dominance-dependency constraint rule: Combination of deep learning and linguistic knowledge (강화된 지배소-의존소 제약규칙을 적용한 의존구문분석 모델 : 심층학습과 언어지식의 결합)

  • JoongMin Shin;Sanghyun Cho;Seunglyul Park;Seongki Choi;Minho Kim;Miyeon Kim;Hyuk-Chul Kwon
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.289-294
    • /
    • 2022
  • 의존구문분석은 문장을 의존관계(의존소-지배소)로 분석하는 구문분석 방법론이다. 현재 사전학습모델을 사용한 전이 학습의 딥러닝이 좋은 성능을 보이며 많이 연구되지만, 데이터셋에 의존적이며 그로 인한 자료부족 문제와 과적합의 문제가 발생한다는 단점이 있다. 본 논문에서는 언어학적 지식에 기반한 강화된 지배소-의존소 제약규칙 에지 알고리즘을 심층학습과 결합한 모델을 제안한다. TTAS 표준 가이드라인 기반 모두의 말뭉치로 평가한 결과, 최대 UAS 96.28, LAS 93.19의 성능을 보였으며, 선행연구 대비 UAS 2.21%, LAS 1.84%의 향상된 결과를 보였다. 또한 적은 데이터셋으로 학습했음에도 8배 많은 데이터셋 학습모델 대비 UAS 0.95%의 향상과 11배 빠른 학습 시간을 보였다. 이를 통해 심층학습과 언어지식의 결합이 딥러닝의 문제점을 해결할 수 있음을 확인하였다.

  • PDF