• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.241-248
• /
• 2007

In this paper, we propose a Transformation-Based Learning (TBL) method on generating the Korean standard pronunciation. Previous studies on the phonological processing have been focused on the phonological rule applications and the finite state automata (Johnson 1984; Kaplan and Kay 1994; Koskenniemi 1983; Bird 1995). In case of Korean computational phonology, some former researches have approached the phonological rule based pronunciation generation system (Lee et al. 2005; Lee 1998). This study suggests a corpus-based and data-oriented rule learning method on generating Korean standard pronunciation. In order to substituting rule-based generation with corpus-based one, an aligned corpus between an input and its pronunciation counterpart has been devised. We conducted an experiment on generating the standard pronunciation with the TBL algorithm, based on this aligned corpus.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2001년도 학술대회 논문집
• /
• pp.231-235
• /
• 2001

Language is not abstract. We use language to communicate out thoughts and emotions. Films are the most public form of arts, where language is all essential part; however, there have been, if any, few films the main theme of which is language. Although language may not be the main theme of films, we can find many kinds of information relating to language and linguistics by careful examination. In reference to some films, we can talk about subjects in the fields of theoretical linguistics such as phonetics, phonology, morphology, syntax, semantics, and pragmatics. In addition, subjects in applied linguistics such as sociolinguistics and computational linguistics may be discussed with reference to other films.

• 한국정보처리학회논문지
• /
• 제4권1호
• /
• pp.280-287
• /
• 1997

성공적인 음성인식·합성 시스템을 구축하기 위해서는 음운론적 지식, 특히 운율 정보의 도입이 매우 중요하다. 본 연구에서는 우선 음성인식·합성을 위한 운율음운 론의 연구동향을 개관하고, 국어의 음운단위와 경계의 설정에 관한 이론적·실험적 고찰을 정리하였으며, 음운단위에 따른 경계의 자동적 발견을 위하여, 데이터를 수집 하고 시스템을 구현하여 실험을 행하였다. 단순회귀 신경망을 이용하여, 2,200여 개 의 문장에 있는 12,000여개의 음운단어를 외부정보의 도움이 전혀 없이 훈련시킨 결 과, 70%정도의 예측률을 보였다. 본 연구에서 사용한 방법을 다른 정보와 결합하여 사용한다면, 음운경계의 발전과 그에 따른 분절화를 정확하게 행할 수 있으리라 기대 된다.

• Journal of Information Processing Systems
• /
• 제1권1호
• /
• pp.41-48
• /
• 2005

This paper presents the development of a morphological processor for the Mongolian language, based on the two-level morphological model which was introduced by Koskenniemi. The aim of the study is to provide Mongolian syntactic parsers with more effective information on word structure of Mongolian words. First hand written rules that are the core of this model are compiled into finite-state transducers by a rule tool. Output of the compiler was edited to clarity by hand whenever necessary. The rules file and lexicon presented in the paper describe the morphology of Mongolian nouns, adjectives and verbs. Although the rules illustrated are not sufficient for accounting all the processes of Mongolian lexical phonology, other necessary rules can be easily added when new words are supplemented to the lexicon file. The theoretical consideration of the paper is concluded in representation of the morphological phenomena of Mongolian by the general, language-independent framework of the two-level morphological model.