• 한국정보처리학회논문지
• /
• 제7권4호
• /
• pp.1132-1140
• /
• 2000

The purpose of this paper was to present the method of progress efficiency of morphosyntaxical analyzer for French information processing in the view of multilingual information processing. This study indicated that he method prohibit the additional useless word type by decomposing word type by decomposing works which were created by morphological amalgamation. Findings also suggested the need of preprocessing in order to decrease the overload of morphosyntaxical analysis algorithm. In addition, general rules were proposed to divide word form and to decompose complex sentence.

• 한국언어정보학회지:언어와정보
• /
• 제5권1호
• /
• pp.87-105
• /
• 2001

This paper categorizes currently available theories of focus into two major types a 'discourse structure approach'(DSA) and a 'sentence structure approach'(SSA) The former DSA is intended to refer to a type of approach that analyzes focus only in terms of the discourse structure in which a focused sentence occurs. The alternative semantics approach which is the most widely available theory of focus belongs to this The latter SSA is meant to refer to a type of theory that analyzes focus in terms of sentence-internal structure, This study supports the SSA be revealing some empirical problems of the DSA that arise is analyzing two different kinds of focus, the A-accented focus and the B-accented focus (contrastive topic), and provides a brief sketch of a comprehensive analysis of focus and contrastive topic.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1999년도 학술발표대회 논문집 제18권 2호
• /
• pp.37-40
• /
• 1999

In this paper, we presented the prosody analysis results of five selected words according to its usage in a sentence, i.e.. the part of sentence (PoS) while changing the type of sentences such as simple, conjugate, and complex sentences. The selected five Korean words were 'U-Ri-Na-Ra' 'Bul-Kuk-Sa', 'Uh-Muh-Ni', 'Han-Ra-San', and 'Cang-A-Ji'. These five words were used as a subjective, an objective, and an adverb in each simple, conjugate, and complex sentence. The pitch, energy, and duration of each word were then analyzed and used for the synthetic speech prosody Improvement. The subjective test on the prosody improvement showed that more than $50\%$ of our listeners are affirmative to the prosody Improvement of the synthetic speech.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 FIFTH WESTERN PACIFIC REGIONAL ACOUSTICS CONFERENCE SEOUL KOREA
• /
• pp.949-956
• /
• 1994

In this paper, we introduce a new speech synthesis method for Japanese and Korean arbitrary sentences using the natural speech data-base. Also, application of this method to a CAI system is discussed. In our synthesis method, a basic sentence and basic accent-phrases are selected from the data-base against a target sentence. Factors for those selections are phrase dependency structure (separation degree), number of morae, type of accent and phonemic labels. The target pitch pattern and phonemic parameter series are generated using those selected basic units. As the pitch pattern is generated using patterns which are directly extracted form real speech, it is expected to be more natural than any other pattern which is estimated by any model. Until now, we have examined this method on Japanese sentence speech and affirmed that the synthetic sound preserves human-like features fairly well. Now we extend this method to Korean sentence speech synthesis. Further more, we are trying to apply this synthesis unit to a CAI system.

• 한국초등과학교육학회지:초등과학교육
• /
• 제29권2호
• /
• pp.134-143
• /
• 2010

The purpose of this study is to devise a new method for examining the readabilities of textbooks and to compare the readabilities of elementary school science textbooks. Third and sixth grade science textbooks were compared in terms of word, sentence, and paragraph in this study. In the word analyses, criterion suggested by Kim (2003) who classified about 238,000 words into seven categories according to their educational importances was adopted. In this study, the words from 3rd and 6th grade science textbooks were classified into four categories, and then the kinds and frequencies of words in each category were investigated. In the sentence analyses, sentences were classified either a simple sentence or a compound/complex sentence, and the ratios of each type were calculated. The average number of words in a sentence was also calculated in the sentence analyses. The ratios of conjunctions and demonstratives were examined in the paragraph analyses. The results indicated that both the kinds and frequencies of words in 3rd grade science textbook were smaller than those of 6th grade one. However, both science textbooks were similar in the distributions of words across the four categories. The ratio of simple sentences in 3rd grade science textbook was higher than that of 6th grade one, and the length of a sentence in 3rd grade science textbook was also shorter than that of 6th grade one. Both the ratios of conjunctions and demonstratives in 3rd grade science textbook were lower than those of 6th grade one.

• 한국언어정보학회지:언어와정보
• /
• 제13권2호
• /
• pp.59-97
• /
• 2009

The type of a given sentence indicates the speaker's attitude towards the listener and is usually determined by its final endings and punctuation marks. However, some 6na1 endings are used in several types of sentences, which means that we cannot identify the sentential type by considering only the final endings and punctuation marks. In this paper, we propose methods of finding some other linguistic clues for indentifying the sentential type with a morphological analysis. We also propose to use these methods to implement a system that automatically classifies sentences in Korean according to their sentential types.

• 음성과학
• /
• 제11권3호
• /
• pp.23-36
• /
• 2004

Many languages show reverse durational variation between preceding vowel and following voiced/voiceless (lax/tense) consonants. This study investigated the likely effects of phoneme type (tense vs. lax) on the timing structure (duration of syllable, word, phrase and sentence) of Korean. Three rates of speech (fast, normal, slow) applied to stimuli with the target word /a-Ca/ where /C/ is one of /p, p', $p^h$/. The type (tense/lax) of /C/ caused marked inverse durational variations in the two syllables /a/ and /Ca/ and highly different durational ratios between them. Words with /p', $p^h$/ were significantly longer than that with /p/, which contrasts with many other languages where such pairs of words have a similar duration. The differentials between words remained up to the phrase and sentence level, but in general the higher linguistic units did not statistically differ within each level. Thus, the phrase is suggested as a compensatory unit of phoneme type effects in Korean. Different rates did not affect the general tendency. Distribution of time variations (from normal to fast and slow) to each syllable (/a/ and /Ca/) was also observed.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 1998년도 제10회 한글 및 한국어 정보처리 학술대회
• /
• pp.217-221
• /
• 1998

본 논문에서는 한국어의 전산처리를 위한 문법 모형 개발의 일부분으로 HPSG에 기반한 문법 모형의 개발을 시도한다. 문법 모형의 개발에는 ALE(Attribute Logic Engine)를 이용하며, 보문 구조와 보조 용언 구문을 분석하기 위한 사전구조 및 문법 규칙을 제시한다. 그리고 문의 종류 (Sentence Type:ST)와 문계(Sentence Level: SL), 시제, 존대 등을 분석해서 표상하기 위한 유형 계층 및 어휘부, 문법 규칙, 문법 원리 등을 제시한다.

• 한국산업정보학회논문지
• /
• 제9권4호
• /
• pp.1-7
• /
• 2004

본 논문에서는 한국어 문장의 구조를 파악하는 데에 결정적인 역할을 하는 조사에 대한 정보를 보다 적극적으로 이용하는 파싱 방법을 기술한다. 이러한 방법을 실현하기 위하여 용언을 세밀하게 분류하였으며, 이를 바탕으로 문장의 형태를 분류하고 이 문장 형태에 필수적으로 나타나는 명사구의 문법적 역할을 파악하는 방법을 이용한 파싱을 시도하였다. 또한, 내부적으로는 언어학적인 틀에서 크게 벗어나지 않는 범위 내에서 약간의 경험지식을 동원하였다. 이를 구현함에 있어서 문법의 수준에서 파싱을 직접 제어하기 위하여 조건단일화 파싱을 사용하였다. 본 논문에서 제시한 파싱 방법은 분석의 초기에 불필요한 가지를 전지함으로써 결과 트리가 간략해져 복잡한 문장의 모호성을 상당두분 제거할 수 있게 해준다.

• 컴퓨터교육학회논문지
• /
• 제13권6호
• /
• pp.79-89
• /
• 2010

본 논문은 한국어 표절 검사를 위해서 표절의 유형을 분석하여, 유형별 분석 결과를 기반으로하여 유사 문장 판별 모델을 제안한다. 제안하는 방법은 한국어 문장에 대한 표절 유형 분석 결과를 토대로 LSA와 N-gram을 이용한 유사 문장 검색을 통하여 여러 유형의 표절로부터 견고한 유사 문장 판별 모델을 구현하였다. 제안한 모델의 성능 분석을 위해서 학생들이 인위적으로 작성한 표절 리포트와 표절한 첨부 문서로 실험 데이터를 구축하였다. 성능 비교를 위해서는 기존의 N-gram 모델, 벡터모델, LSA 모델이 사용되었으며, 실험 결과 제안한 모델이 정확률, 재현율, 그리고 F값 척도에서 우수한 성능을 보임을 알 수 있었다.