• 한국도서관정보학회지
• /
• 제12권
• /
• pp.199-232
• /
• 1985

Word processor having the functions of a typewriter and a computer together have been used as a powerful tools for office automation. The purpose of this study is to find out the possible areas of the word processing a n.0, pplication in the library operations. For the study, the general concept, developmental process, structure, functions, kinds and suggested a n.0, pplicable areas in the library operations of word processor were investigated. Then, the cases of real a n.0, pplications of word processor in the library field were examplified. In conclusion, the areas where word processor can be of benefit to library workers can be summarized as follows, 1) Orders of books and periodical acquisitions, 2) On-line searching, and storage and editing of input as required, 3) Production of catalogues, and abstracting and indexing bulletin, 4) Budget control, circulation control, and serial control.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.136-146
• /
• 1995

In this paper, a Japanese morphological analyzer for Japanese to Korean Machine Translation System is designed. The analyzer reconstructs the Japanese input sentence into word phrases that include grammatical and dictionary informations. Thus we propose the algorithm to separate morphemes and then connect them by reference to a corresponding Korean word phrases. And we define the connector to control Japanese word phrases It is used in controlling the start and the end point of the word phrase in the Japanese sentence which is without a space. The proposed analyzer uses the analysis dictionary to perform more efficient analysis than the existing analyzer. And we can decrease the number of its dictionary searches. Since the analyzer, proposed in this paper, for Japanese to Korean Machine Translation System processes each word phrase in consideration of the corresponding Korean word phrase, it can generate more accurate Korean expressions than the existing one which places great importance on the generation of the entire sentence structure.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(3)
• /
• pp.165-168
• /
• 2000

First, we give a linear-time algorithm to find the first overlap in an arbitrary binary word. Second, we implement the algorithm in the C language and show that the number of comparisons in this algorithm is less than 31n, where n$\geq$3 is the length of the input word.

• 전자공학회논문지C
• /
• 제35C권11호
• /
• pp.63-75
• /
• 1998

한국어 연속 음성에서 발생하는 조음결합문제를 해결하기 위하여 단어를 기본 인식 단위로 사용할 경우 각 단어의 효율적인 표현 방법, 연속된 단어로 이루어진 여러 문장의 표현 방법 그리고 입력된 연속음성을 연속된 여러 단어로의 정합 방법에 관한 연구가 선행되어야 한다. 본 논문에서는 은닉 마르코프 모델과 레벨빌딩 알고리즘을 이용한 한국어 연속 음성 인식 시스템을 제안한다. 각 단어는 은닉 마르코프 모델로 표현하고 문장을 표현하기 위하여 단어 모델을 연결한 형태인 인식 네트워크를 구성한다. 인식네트워크의 탐색 알고리즘으로는 레벨 빌딩 알고리즘을 사용한다. 제안한 방법은 항공기 예약 시스템에 적용한 실험에서 인식율과 인식속도면에서 실용적이었으며 또한 비교적 적은 저장공간으로 전체 문장을 표현하고 쉽게 확장할 수 있다는 장점을 가지고 있다.

• 한국음향학회지
• /
• 제10권1호
• /
• pp.82-91
• /
• 1991

본 논문에서는, 후지쯔의 음성 자동인식 관련 제품 개발의 역사, 현재의 상품, 그리고 앞으로의 연구 개발에 대해서 소개한다. 현재는 4,000단어로 부터 12,000단어를 인식하는 특정 화자형의 F2360, 17단어를 인식하는 불특정 화자형의 F2355 L/S를 판매하고 있으며, 앞으로의 연구 개발로는 음소 변형에 적극적으로 대처하고, 자연적인 발성을 인식하기 위한 기초 기술을 개발할 계획에 있다. 인식할 단어의 문자 표기에 음향 segment 변형 규칙을 적용하여 음향 segment network를 자동 생산하여서 입력 음성과의 조합을 행한다. 이 기초 기술을 대어휘 단어 음성 인식에 응용하기 위해서 필요한 단어 후보 선택 방식, 문절 발성을 문장 입력에 응용하기 위한 문절 후보 생성 방식과 문 검사 방식에 대해서도 서술한다.

• 한국지역사회생활과학회지
• /
• 제17권3호
• /
• pp.3-14
• /
• 2006

The purpose of this study was to investigate the relationship between conversational function and question type in mothers' utterances and their infant's language development. The subjects were 20 infants from 1;07 to 1;11 years of age in Yanji, China. Each child's spontaneous natural speech during interaction with his/her mother was videotaped for about 30 minutes. The children and their mother's spontaneous utterances were transcribed and coded for the number of type and token of word, grammatical morpheme conversational function and type of question in mother's language input to her child. The result showed that mothers used questions as the most frequent conversational function with their infants. The number of questions in conversational function in mothers' utterances positively correlated with the type of word, type of morpheme and grammatical morpheme in infants' utterance. However, there was no correlation between mothers' language input and infant early language development.

• ETRI Journal
• /
• 제45권1호
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• 말소리와 음성과학
• /
• 제3권1호
• /
• pp.3-14
• /
• 2011

It has been posited that in English, native listeners use the Metrical Segmentation Strategy (MSS) for the segmentation of continuous speech. Strong syllables tend to be perceived as potential word onsets for English native speakers, which is due to the high proportion of strong syllables word-initially in the English vocabulary. This study investigates whether Koreans employ the same strategy when segmenting speech input in English. Word-spotting experiments were conducted using vowel-initial and consonant-initial bisyllabic targets embedded in nonsense trisyllables in Experiment 1 and 2, respectively. The effect of strong syllable was significant in the RT (reaction times) analysis but not in the error analysis. In both experiments, Korean listeners detected words more slowly when the word-initial syllable is strong (stressed) than when it is weak (unstressed). However, the error analysis showed that there was no effect of initial stress in Experiment 1 and in the item (F2) analysis in Experiment 2. Only the subject (F1) analysis in Experiment 2 showed that the participants made more errors when the word starts with a strong syllable. These findings suggest that Koran listeners do not use the Metrical Segmentation Strategy for segmenting English speech. They do not treat strong syllables as word beginnings, but rather have difficulties recognizing words when the word starts with a strong syllable. These results are discussed in terms of intonational properties of Korean prosodic phrases which are found to serve as lexical segmentation cues in the Korean language.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.254-276
• /
• 2019

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, the researchers are paying much attention to Document Summarization. The key point in any successful document summarizer is a good document representation. The traditional approaches based on word overlapping mostly fail to produce that kind of representation. Word embedding has shown good performance allowing words to match on a semantic level. Naively concatenating word embeddings makes common words dominant which in turn diminish the representation quality. In this paper, we employ word embeddings to improve the weighting schemes for calculating the Latent Semantic Analysis input matrix. Two embedding-based weighting schemes are proposed and then combined to calculate the values of this matrix. They are modified versions of the augment weight and the entropy frequency that combine the strength of traditional weighting schemes and word embedding. The proposed approach is evaluated on three English datasets, DUC 2002, DUC 2004 and Multilingual 2015 Single-document Summarization. Experimental results on the three datasets show that the proposed model achieved competitive performance compared to the state-of-the-art leading to a conclusion that it provides a better document representation and a better document summary as a result.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1983년도 춘계학술발표회논문집
• /
• pp.18-28
• /
• 1983

This paper describes the result of a series of fundamental researches on a word processing system, named WORD80. Given the text consisting of Ilanguel characters, Chinese characters, English alphabets and other special characters, it can provide-ㄴo-see printout, after having processed according to the commands used to control the output format of the text. Since each Hanguel character in input text is made up of and is represented as some compoents, it uses the deterministic finite automata for the formation of Hanguel from its components. When developed at first, the WORD80 can perform Hanguel to Chinese transition character by character by character. But it was thought to be more practical to do this word by word.