• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.429-432
• /
• 2007

정보화 시대에 범람하는 정보들 중 원하는 정보를 빠르고 정확하게 검색할 수 있도록 도와주는 정보검색 시스템의 중요성이 대두 되고 있다. 정보 검색 시스템의 한 축을 담당하는 색인어 추출기는 보통 형태소 분석을 통하여 작성이 되지만 색인어 추출만을 위하여선 불필요한 작업들이 있는 것이 사실이다. 그래서 이 논문에서는 미리 정의된 색인어 리스트를 가진 사전을 이용한 색인어 추출 시스템을 제안하고 그에 맞는 데이터 구조들을 분석하여 성능 비교를 하였다.

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.257-268
• /
• 2011

We define a 'dominant emotion' as acting dominantly for unit time, and propose methodology to extract dominant emotion in a literature automatically. Due to the nature of the Korean language, it is able to be changed or reversed owns meanings as desinence. But it might be possible to extract a dominant emotion in a text has a small quantity like a fiction or an essay. A process to extract a dominant emotion in a literature is as follows. At first, extract morphemes in a whole text. And dispart words having emotional meaning as matching emotion terms database. Map disported terms to a affective circumplex model and matching it with basic emotion. Finally, analyze dominant emotion according to matched basic emotion. And we adjust our methodology to two literature; modem fiction 'A lucky day' by Jingeon, Hyun and essay 'An old man who shave a bat' by Woyoung, Yun. As a result, it was possible to grasp flows of dominant emotion.

• Proceedings of the KAIS Fall Conference
• /
• 2003.06a
• /
• pp.284-287
• /
• 2003

본 논문은 시각 장애인을 위해 양면 인쇄된 점자를 스캐너를 통해서 읽어 들인 후, 영상 내의 잡음과 같은 미세 정보를 제거하는 전처리과정을 거친다 스캔한 영상을 임계값을 이용한 클리핑으로 이진영상을 만든 후 영상의 특징을 추출한다. 추출된 특징은 점자의 앞면과 뒷면으로 분류할 수 있다. 점자 앞면의 특징이 아래반원으로 나타나며 이러한 특징을 이용한 검출필터를 만들어 점자의 앞면만을 추출해낸다. 영상을 각각 수직방향, 수평방향으로 투영시켜 점자영상 분할을 위한 거리를 계산, 자간격과 줄간격을 구해 ½되는 지점에 선을 그어 분할한다. 분할된 점자 형태소를 낱자로 인식한다.

• Journal of the Korean Society for information Management
• /
• v.13 no.1
• /
• pp.47-63
• /
• 1996

Conventional automatic indexing methods for Hangul texts can be classified into two groups as follows: One is to extract index terms by removing non-indexable segments from word-phrases, and the other is to generate index terms from the morphemes of word-phrases. The former suffers from the problem of word boundaries when documents contain many compound nouns. The latter can overcome the word boundary problem by extracting simple nouns, but has many overheads to develop a lot of linguistic knowledges needed in the indexing procedure. In this paper we propose a new indexing method based on n-grams. This method alleviates the problems of previous indexing methods related with word boundaries and linguistic knowledges. We also compare the effectiveness of the n-gram based indexing method with that of the previous ones.

• The Journal of Society for e-Business Studies
• /
• v.23 no.2
• /
• pp.83-96
• /
• 2018

Extracting keywords representing documents is very important because it can be used for automated services such as document search, classification, recommendation system as well as quickly transmitting document information. However, when extracting keywords based on the frequency of words appearing in a web site documents and graph algorithms based on the co-occurrence of words, the problem of containing various words that are not related to the topic potentially in the web page structure, There is a difficulty in extracting the semantic keyword due to the limit of the performance of the Korean tokenizer. In this paper, we propose a method to select candidate keywords based on semantic similarity, and solve the problem that semantic keyword can not be extracted and the accuracy of Korean tokenizer analysis is poor. Finally, we use the technique of extracting final semantic keywords through filtering process to remove inconsistent keywords. Experimental results through real web pages of small business show that the performance of the proposed method is improved by 34.52% over the statistical similarity based keyword selection technique. Therefore, it is confirmed that the performance of extracting keywords from documents is improved by considering semantic similarity between words and removing inconsistent keywords.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.373-375
• /
• 2021

In the case of Korean, the possibility of development is lower than that of English if tagging is done through the word tokenization like English. Although the form of tokenizing the corpus by separating it into morpheme units via KoNLPy is represented as a graph database, full separation of voice files and verification of practicality is required when converting the module from graph database to corpus. In this paper, morphology representation using STT API is shown in Raspberry Pi. The voice file converted to Corpus is analyzed to KoNLPy and tagged. The analyzed results are represented by graph databases and can be divided into tokens divided by morpheme, and it is judged that data mining extraction with specific purpose is possible by determining practicality and degree of separation.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.213-215
• /
• 2015

국립국어원 온라인가나다에서 제공되는 질의응답 문서를 이용한 국어정보에 대한 Q&A시스템은 언어 자체에 대한 질문과 답변의 특성으로 조사나 어미로 끝나는 표현이 주어로 등장하는 등의 특이한 문장이 자주 나타난다. 이러한 이유로 형태소 분석을 거쳐 명사를 키워드로 추출하는 일반적인 키워드 추출 방식은 좋은 성능을 얻기 어렵다. 본 논문에서는 국어정보 질의응답 문서의 특징에 맞는 키워드 추출 방법을 제안한다. 제안하는 방식에서는 문장 단위로 분할된 결과에서 연결어미로 문장을 추가로 분할한 뒤에 조사 앞에 나타나는 단어열을 키워드로 추출한다. 덧붙여 다자비교형 질의에서의 키워드 추출을 위해 편집거리를 이용한 키워드 추출 방법을 제안한다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.10
• /
• pp.1183-1192
• /
• 1988

In this paper, we describe heuristic information-added morphological dictionary and connection table, and automatic MUNJEUL separation process on the basis of least cost method for efficient morphological analysis. It is simplified the composition of connection and inflective word information by mutually interconnect conjugation table with connection tables. As a result, the applicability of system is increased. Translation dictionary consists of analysis and generation part and, increase the applicability by describing frequently using termination phrase which is extracted statistically as idiom and the procedure directly on the dictionary for the efficiency of analysis process and more natural generation of translation sentence.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10a
• /
• pp.269-272
• /
• 2000

본 논문에서는 ETRI에서 개발 중인 용언구에 기반한 한영 기계번역 시스템 CaptionEye/KE에 대하여 논술한다. CaptionEye/KE는 대량의 고품질 한-영 양방향 코퍼스로부터 추출된 격틀사전 및 대역패턴, 대역문 연결패턴 등의 언어 지식들을 바탕으로 하여, 한국어의 용언구 단위의 번역을 조합하여 전체 번역을 수행한다. CaptionEye/KE는 변환방식의 기계번역 시스템으로서, 크게 한국어 형태소 분석기, 한국어 구문 분석기, 부분 대역문 연결기, 부분 대역문 생성기, 대역문 선택/정련기, 영어형태소 생성기로 구성된다. 입력된 한국어 문장에 대해 형태소 분석 및 태깅을 수행한 후, 격틀사전을 이용하여 구문구조를 분석하고 의존 트리를 생성해 낸다. 이렇게 생성된 의존 트리로부터 대역문 연결패턴을 이용하여 용언구들간의 연결에 대한 번역을 수행한 후 대역패턴을 이용하여 각 용언구들을 번역하고 문장 정련과정을 거쳐 영어 문장을 최종 생성한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.4
• /
• pp.2764-2769
• /
• 2015

In this paper, we present a Korean syntactic analysis system which can generate all possible syntactic trees in a given sentence. Therefore, the number of syntactic trees by this syntactic analysis system can be increased exponentially. To solve this problem, we suggest a segmentation method and maximum connected unit in a segmentation. Maximum connected unit is a combined unit which contains all morphemes in a segmentation. According to the input sentence, it is possible one or more maximum connected unit in a segmentation. We extract 516 sentences to experiment randomly from the text book of Korean middle school. We could reduce about 28% of the number of syntactic trees.