• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4241-4254
• /
• 2019

The efficiency and accuracy of handwriting measurement could be improved by adopting digital image processing. This study developed a computer-based Korean Handwriting Assessment tool. Second graders participated in this study by performing writing tasks of consonants, vowels, words, and sentences. We extracted boundary parameters for each letter using digital image processing and calculated the variables of size, size coefficient of variation (CV), misalignment, inter-letter space, inter-word space, and ratio of inter-letter space to inter-word space. Children were also administered traditional handwriting and visuomotor tests. Digital variables from image processing were correlated with these previous tests. Using these correlations, we established a three-point scoring system that computed test scores for each variable. We analyzed inter-rater reliability between the computer rater and human rater and test-retest reliability between the first and second performances. The validity was examined by analyzing the relationship between the Korean Handwriting Assessment and previous handwriting and visuomotor tests. We suggested the Korean Handwriting Assessment to measure size, size consistency, misalignment, inter-letter space, inter-word space, and space ratio using digital image processing. This Korean Handwriting Assessment tool proved to have reliability and validity. It is expected to be useful for assessing children's handwriting.

• 음성과학
• /
• 제2권
• /
• pp.159-172
• /
• 1997

This paper proposes a prosodic representation system of the Kyungnam dialect of Korean, based on the ToBI system. In this system, diverse intonation patterns are transcribed on the four parallel tiers: a tone tier, a break index tier, an orthographic tier, and a miscellaneous tier. The tone tier employs pitch accents, phrase accents, and boundary tones marked with diacritics in order to represent various pitch events. The break index tier uses five break indices, numbered from 0 to 4, in order to represent degrees of connectiveness in speech by associating each inter-word position with a break index. In this, each break index represents a boundary of some kind of constituent. This system can contribute not only to a more detailed theory connecting prosody, syntax, and intonation, but also to current text-to-speech synthesis approaches, speech recognition, and other quantitative computational modellings.

• 대한임베디드공학회논문지
• /
• 제17권4호
• /
• pp.199-208
• /
• 2022

Korean is an agglutinative language, and one or more morphemes are combined to form a single word. Part-of-speech tagging method separates each morpheme from a word and attaches a part-of-speech tag. In this study, we propose a new Korean part-of-speech tagging method based on the Head-Tail tokenization technique that divides a word into a lexical morpheme part and a grammatical morpheme part without decomposing compound words. In this method, the Head-Tail is divided by the syllable boundary without restoring irregular deformation or abbreviated syllables. Korean part-of-speech tagger was implemented using the Head-Tail tokenization and deep learning technique. In order to solve the problem that a large number of complex tags are generated due to the segmented tags and the tagging accuracy is low, we reduced the number of tags to a complex tag composed of large classification tags, and as a result, we improved the tagging accuracy. The performance of the Head-Tail part-of-speech tagger was experimented by using BERT, syllable bigram, and subword bigram embedding, and both syllable bigram and subword bigram embedding showed improvement in performance compared to general BERT. Part-of-speech tagging was performed by integrating the Head-Tail tokenization model and the simplified part-of-speech tagging model, achieving 98.99% word unit accuracy and 99.08% token unit accuracy. As a result of the experiment, it was found that the performance of part-of-speech tagging improved when the maximum token length was limited to twice the number of words.

• 인지과학
• /
• 제34권4호
• /
• pp.315-347
• /
• 2023

이 연구는 시선 추적의 경계선 기법을 사용하여, 자연스러운 읽기 과정에서 중심와주변에 제시된 단어의 표기체계와 의미 정보가 표적 단어의 읽기에 미치는 영향을 알아보았다. 참가자는 중국어와 한국어 이중언어자였고, 읽기 문장은 한국어 단어와 중국어 단어가 혼용된 문장이었다. 참가자들의 읽기 과정은 안구 운동 추적 도구 EyelinkII를 통해 모니터링되었다. 화면에는 전체 문장이 제시되었고, 시선이 표적 위치로 이동하기 직전에 미리 제시되어 있던 미리보기 단어가 표적단어로 대체되었다. 표적단어는 언제나 한글 단어였고, 미리보기 단어는 (1) 표적단어와 동일 단어(예: 나라), (2) 동일 의미의 한자어 단어(예: 국가) (3) 동일 의미의 중국어 단어(예: 国家), (4) 무관련 중국어 단어(예: 围裙)였다. 2)와 3) 조건은 같은 단어로 표기 체계만 한글과 한자로 달랐다. 주요 측정치는 표적 단어에 시선이 고정되는 시간이었고, 동일 단어, 동일 의미 한자어 단어 그리고 동일 의미 중국어 단어 조건의 고정시간은 무관련 중국어 조건에서보다 짧았으며 주시시간은 동일한 의미 중국어 단어 조건에서 동일 단어 조건보다 짧게 관찰되었다. 이 결과는 중국어-한국어 이중 언어 사용자들이 중심와주변에서 의미 정보를 추출할 수 있음을 시사하고 중심와주변에 제시된 단어의 표기법과 의미 정보가 모두 읽기에 영향을 주었음을 보여준다.

• 한국음향학회지
• /
• 제15권6호
• /
• pp.26-32
• /
• 1996

본 논문은 자연스러운 여성 합성음을 위한 피치 변화 법칙을 세웠다. 피치 변화 법칙이 적용되는 기본 단위, 즉 억양구는 주로 어절(들)로 이것의 첫번째, 두번째, 마지막 음절의 피치값을 연결해 피치 변화 곡선을 형성하였는데, 첫번째, 두번째 음절의 피치값은 각 음절의 초성에 따라, 마지막 음절의 피치값은 기능어의 종류에 따라 결정되었다. 억양구 사이에는 '쉼(pause)이 있는 경계' 또는 '쉼이 없는 경계'가 오며, 쉼이 있는 경계에는 relaxation이 있다. 이러한 억양구의 피치 변화 곡선, 경계 현상들이 모여 한 문장의 피치 턴을 만들었다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권11호
• /
• pp.441-448
• /
• 2019

기존의 자동 띄어쓰기 연구는 n-gram 기반의 통계적인 기법을 이용하거나 형태소 분석기를 이용하여 어절 경계면에 공백을 삽입하는 방법으로 띄어쓰기 오류를 수정한다. 본 논문에서는 심층 신경망을 이용한 종단 간(end-to-end) 한국어 문장 자동 띄어쓰기 시스템을 제안한다. 자동 띄어쓰기 문제를 어절 단위가 아닌 음절 단위 태그 분류 문제로 정의하고 음절 unigram 임베딩과 양방향 LSTM Encoder로 문장 음절간의 양방향 의존 관계 정보를 고정된 길이의 문맥 자질 벡터로 연속적인 벡터 공간에 표현한다. 그리고 새로이 표현한 문맥 자질 벡터를 자동 띄어쓰기 태그(B 또는 I)로 분류한 후 B 태그 앞에 공백을 삽입하는 방법으로 한국어 문장의 자동 띄어쓰기를 수행하였다. 자동 띄어쓰기 태그 분류를 위해 전방향 신경망, 신경망 언어 모델, 그리고 선형 체인 CRF의 세 가지 방법의 분류 망에 따라 세 가지 심층 신경망 모델을 구성하고 종단 간 한국어 자동 띄어쓰기 시스템의 성능을 비교하였다. 세 가지 심층 신경망 모델에서 분류 망으로 선형체인 CRF를 이용한 심층 신경망 모델이 더 우수함을 보였다. 학습 및 테스트 말뭉치로는 최근에 구축된 대용량 한국어 원시 말뭉치로 KCC150을 사용하였다.

• 음성과학
• /
• 제15권4호
• /
• pp.43-60
• /
• 2008

Instrumental studies (e.g., aerodynamic, EPG, and EMMA) have shown that the first of two stops in sequence can be articulatorily reduced in time and space sometimes; either gradient or categorical. The current EMMA study aims to examine possible factors_linguistic (e.g., speech rate, word boundary, and prosodic boundary) and paralinguistic (e.g., natural context and repetition)_to induce gradient reduction of $C_1$ in /pk/ cluster sequences. EMMA data are collected from five Seoul-Korean speakers. The results show that gradient reduction of lip aperture seldom occurs, being quite restricted both in speaker frequency and in token frequency. The results also suggest that the place assimilation is not a lexical process, implying that speakers have not fully developed this process to be phonologized in the abstract level.

• 한국실내디자인학회논문집
• /
• 제27권3호
• /
• pp.108-115
• /
• 2018

The atmosphere is a popular word in everyday life. There is often an atmosphere when we enter a particular place. As if to say, The mood is perceived as an emotional and subjective word. Atmosphere is subjective and there are different feelings, but there are definitely certain feelings that people can relate to. The researcher examines the question in the paper and analyzes how the atmosphere in the space could be explained. So I will research about $B{\ddot{o}}hme^{\prime}s$ aesthetics which is called atmosphere. and analysis how his atmosphere is applied in nowadays art. So this study has two purposes. First is the notion of the atmosphere, not the atmosphere of rational perspective, it's about emotional and perceptual experiences. Therefore a connection about audience and arts is the most important focus in atmosphere. So the other purpose is Olafur Eliasson's Atmosphere. he is an artist about this perception. His work requires spectator intervention and participation to make it a perfect art. There is also a element in Eliasson's philosophy, in which the perceptual experiences of visitor's relationship between the work and the viewer, and eliminates the boundary as a perceptual expression.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2012-2030
• /
• 2021

Named Entity Recognition (NER) is used to identify entity nouns in the corpus such as Location, Person and Organization, etc. NER is also an important basic of research in various natural language fields. The processing of Chinese NER has some unique difficulties, for example, there is no obvious segmentation boundary between each Chinese character in a Chinese sentence. The Chinese NER task is often combined with Chinese word segmentation, and so on. In response to these problems, we summarize the recognition methods of Chinese NER. In this review, we first introduce the sequence labeling system and evaluation metrics of NER. Then, we divide Chinese NER methods into rule-based methods, statistics-based machine learning methods and deep learning-based methods. Subsequently, we analyze in detail the model framework based on deep learning and the typical Chinese NER methods. Finally, we put forward the current challenges and future research directions of Chinese NER technology.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권6호
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.