http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
온톨로지(Ontology)를 기반으로 하는 개념구조와 어휘기술
신효필 서울대학교 어학연구소 2004 語學硏究 Vol.40 No.3
In this paper, I suggest a way of mapping the Mikrokosmos Ontology being developed at CRL (Computing Research Lab) of New Mexico State University, into lexical items. Many extensions to the Korean lexical meaning classifications have largely relied on the noun classifications and conceptual considerations. Those approaches, however, have proven to be insufficient in the case of Korean because lexical meaning classifications hardly fit in with conceptual structures. Along the same lines, simple meaning classification itself does not contribute to either theoretical linguistics or natural language processing. To resolve this problem, I introduce the language-independent conceptual structures, the Mikrokosmos ontology, which contain about 5,000 concepts encapsulating various lexical information in a frame. And I show how to map each individual sense of a word into the corresponding conceptual structure. Adopting this approach to Korean is an even greater challenge because Korean is such a polysemous complicated language. The ontology-based conceptual structure and its mapping to the lexical items allow us to disambiguate polysemous words and come up with unified ways of lexicon building.
Specifications and Analysis of the Korean Sentiment Analysis Corpus
신효필,김문형 서울대학교 언어교육원 2013 語學硏究 Vol.49 No.2
This paper describes the two year endeavor of constructing the Korean Sentiment Analysis Corpus (KOSAC), focusing on the theoretical background and the analysis of the corpus itself. Our aim is to provide a solid theoretical background for the corpus which reflects the characteristics of the Korean language and includes approximately 7,744 sentences taken from news articles. The corpus annotation scheme, based on the MPQA, is described along with the statistics of features specified in the corpus. The analysis of the corpus can be a starting point for how to utilize the corpus not only for sentiment analysis but also for semantic or pragmatic work in terms of speaker’s attitude and emotional expressions.
A Corpus Study of Nested Sources for Subjectivity Analysis
신효필 사단법인 한국언어학회 2014 언어학 Vol.0 No.69
This paper presents a study of subjective and objective language witha focus on speaker’s attitude in terms of epistemological stance in modality. We investigated the degree of subjectivity according to nested sources andprovided the statistical evidence from the MPQA and the KOSAC corpus. Inthe simple corpus analysis, we found that individual numbers of nested sourcescan be one of the factors to identify the difference between subjective andobjective sentences. The analysis from this research suggests a new modality orpragmatics-based methodology to extract patterns for subjectivity or objectivityby resorting to Source Introducing Predicates and nested sources.