• Annual Conference on Human and Language Technology
• /
• 1996.10a
• /
• pp.246-252
• /
• 1996

한국어 형태소 분석기의 효율성에 영향을 미치는 요인은 분석 알고리즘의 효율성보다도 어휘 사전 등 형태소 분석과 관련된 여러 가지 요인들이 미치는 영향이 훨씬 더 크다. 따라서 단어의 유형 분류 기법이나 불규칙 용언의 분석 방법을 비롯하여 어휘 사전의 구조 및 크기, 알고리즘의 선택과 구현 등 형태소 분석과 관련된 모든 요소들을 형태소 분석에 적합하도록 구성하여야 한다. 본 논문에서는 어휘형태소 사전과 문법형태소 사전의 크기, 한글 문서에 나타나는 단어의 특성 등 형태소 분석기의 효율 및 성능에 영향을 미치는 요소들을 고찰하였다. 그 결과로 알고리즘의 효율보다는 사전 탐색 시간이 형태소 분석에 미치는 영향이 매우 크다는 것을 알 수 있었다. 이와 같이 형태소 분석기의 성능에 영향을 미치는 요인들을 고려하여 구현된 범용 형태소 분석기 HAM에 대하여 형태소 분석 기능과 철자 검사 기능을 실험하였다. 형태소 분석 성공률에 대한 실험 결과 99.46%의 분석률을 보이고 있으며, 맞춤법 검사 기능으로는 상용화된 철자 검사기와 비슷한 성능을 보이고 있다. HAM의 처리 속도는 pentium 120MHz linux 2.0 환경에서 1 초에 약 1,000 단어를 분석한다.

• Applied Chemistry for Engineering
• /
• v.30 no.5
• /
• pp.639-642
• /
• 2019

Hydroxyapatite (HAP) containing hexadecyltrimethylammonium chloride (CTAC) as a cationic surfactant was prepared by a precipitation method. X-ray diffraction (XRD), transmission electron microscopy (TEM) and micropore physisorption analyzer were used for characterizing the crystal phase, morphology and specific surface area of HAP and CTAC-HAP. After thermal treatment, the specific surface area of both pure HAP and CTAC-HAP were reduced. The sharp rod morphology of CTAC-HAP was changed into a round shape with a smaller aspect ratio after the heat treatment. The morphological change by thermal treatment was also observed in pure HAP. Therefore, the morphological change and decrease of the specific surface area suggested that pores from the removal of CTAC during thermal treatment were not retained.

• Journal of KIISE:Software and Applications
• /
• v.37 no.12
• /
• pp.946-950
• /
• 2010

Many sentiment categorization systems based on machine learning methods use morphological analyzers in order to extract linguistic features from sentences. However, the morphological analyzers do not generally perform well in a customer review domain because online customer reviews include many spacing errors and spelling errors. These low performances of the underlying systems lead to performance decreases of the sentiment categorization systems. To resolve this problem, we propose a feature extraction method based on simple longest matching of Eojeol (a Korean spacing unit) and phoneme patterns. The two kinds of patterns are automatically constructed from a large amount of POS (part-of-speech) tagged corpus. Eojeol patterns consist of Eojeols including content words such as nouns and verbs. Phoneme patterns consist of leading consonant and vowel pairs of predicate words such as verbs and adjectives because spelling errors seldom occur in leading consonants and vowels. To evaluate the proposed method, we implemented a sentiment categorization system using a SVM (Support Vector Machine) as a machine learner. In the experiment with Korean customer reviews, the sentiment categorization system using the proposed method outperformed that using a morphological analyzer as a feature extractor.

• MALSORI
• /
• no.46
• /
• pp.51-64
• /
• 2003

In order to produce high quality synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model from texts using natural language processing. Robust preprocessing for non-Korean characters should also be required. In this paper, we analyzed Korean texts using a morphological analyzer, part-of-speech tagger and syntactic chunker. We present a new grapheme-to-phoneme conversion method for Korean using a hybrid method with a phonetic pattern dictionary and CCV (consonant vowel) LTS (letter to sound) rules, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method. The probabilistic method atone usually suffers from performance degradation due to inherent data sparseness problems. So we adopted tree-based error correction to overcome these training data limitations.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.89-103
• /
• 1999

It is relatively easy to develop a prototype of a Korean language processing system, but it is very difficult to make it an operational system. In this paper, we survey the current status and methodological issues of the Korean language processing systems such as morphological analyzer, parser and machine translator. In most cases, Korean language processing system easily comes to a dead-end state where its performance can not be improved any more. The reason is that it adopts a general algorithm covering similar problems as a whole because specific low-level problems are not clearly defined and their algorithms are unclear. So, when we add some restrictions to solve an individual linguistic problem, they are also applied to other linguistic phenomena as a side effect. It causes a critical problem that the improvement of the algorithm is very difficult. This paper proposes a 2-step paradigm, a divide-and-conquer method by the functional modularization, a simplification method, and an exception handling technique to develop an operational system that does not fall into a dead-end state.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.87-90
• /
• 2003

In order to produce high quality synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model from texts using natural language processing. Robust preprocessing for non-Korean characters should also be required. In this paper, we analyzed Korean texts using a morphological analyzer, part-of-speech tagger and syntactic chunker. We present a new grapheme-to-phoneme conversion method, i.e. a dictionary-based and rule-based hybrid method, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method.

• The Transactions of the Korea Information Processing Society
• /
• v.1 no.1
• /
• pp.129-139
• /
• 1994

This paper presents a morphological analysis method for the Korean language. The characteristics and adjacency information of the words can be obtained from sentences in a large corpus. Generally a word can be analyzed to a result by applying the adjacency attributes and rules. However, we have to choose one from the several results for the ambiguous words. The collected morpheme's adjacency attributes and relations with neighbor words are recorded in a well designed dictionaries. With this information, abbreviated words as well as ambiguous words can be almost analyzed successfully. Efficiency of morphological analyzer depends on the information in the dictionaries. A morpheme dictionary and a phrase dictionary have been designed with lexical database, and necessary information extracted from the corpus is stored in the dictionaries.

• Korean Journal of Cognitive Science
• /
• v.3 no.1
• /
• pp.25-39
• /
• 1991

When an ending which begins with 'a/a'combines to a stem,'a/a'can be deleted.Especially when ot combines to an h-irregular verb,it is represented as a variant like '-a-','-e-','-ia-',or'-ie-'.In order to analyze the variants of 'a/a',we suggest the format of a grammatical morpheme dictionary which is represented as a binary tree and several procedures which process the variants so that the unexpected errors can be removed which occur frequently when we analyze Korean worl phrase.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.279-284
• /
• 2008

본 연구에서는 어절패턴을 이용하는 새로운 방식의 한국어 형태소 분석기 KGuru-MA에 대해서 설명한다. KGuru-MA는 품사 부착 말뭉치에서 개방어를 생략하여 어절 패턴을 반자동으로 학습하여 어절 패턴 사전과 형태소 확률 정보 사전을 구성한 후, 이 사전을 이용하여 형태소를 분석한다. 본 형태소 분석기는 어절패턴을 사용하여 형태소 분석하기 때문에 기존 형태소 분석기에 존재하는 접속검사 과정이 생략된다. 또한, 형태소 분석 과정이 기존의 형태소 분석기에 비해 단순하여 기초 자연언어 처리 시스템이 가지는 강건성을 보장한다. 본 연구는 "21세기 세종기획 3차년도 말뭉치"를 이용한 실험 결과, 기존 형태소 분석기 못지 않은 성능을 보였다.

• Journal of Korean Library and Information Science Society
• /
• v.35 no.3
• /
• pp.271-291
• /
• 2004

Such information services source like digital library has been asked information services of atypical multimedia database like image, voice, VOD/AOD. Examined in this study are suggestions such as word-phrase generator, syllable recoverer, morphological analyzer, corrector for voice processing. Suggested voice processing technique transform voice database into tort database, then extract index database from text database. On top of this, the study suggest a information retrieval model to use in extracted index database, voice full-text information retrieval.