한국어 정보처리 : 국어사전을 이용한 한국어 명사에 대한 상위어 자동 추출 및 WordNet 의 프로토타입 개발

김민수(Kim Min Soo),김태연(Kim Tae Yeon),노봉남(Noh Bong Nam) 한국정보처리학회 1995 정보처리학회논문지 Vol.2 No.6

인간은 문장 안에 있는 명사를 인식할 때 그 명사의 상위 개념을 머리에 떠올린다. 컴퓨터에게 인간의 단어 인식작용을 시뮬레이션하기 위해서는 단어의 상위 개념(상위어)을 지식 베이스(WordNet)로 구축해야만 한다. 현재 한국에서는 많은 인력과 시간이 소요되기 때문에 WordNet의 작업을 시작하지 못하였으나, 컴퓨터의 성능이 급격히 향상되고 상용화된 MRD(Machine Readable Dictionary)가 이용가능하게 됨에 따라 자동으로 WordNet구축의 가능성을 보이고 있다. 본 논문에서는 한국어 MRD(Machine Readable Dictionary)의 명사의 정의(description)를 이용하여 자동으로 한국어 명사 WordNet을 구축하는 방법을 제안한다. 한국어 문장의 구조적인 특징을 분석하여 상위 개념(상위어)를 추출하는 규칙을 제안한다. 그것은 중심적인 말이 보통 뒤에 나타난다는 것과 명사의 정의문은 특수한 구조를 갖는다는 것을 반영하였다. 또한, 이러한 규칙에 의해 만들어진 상위어들을 결합한 한국어 명사의 WordNet 프로토타입을 개발하였다. 약 2500개 표본 단어의 상위어를 추출한 결과 약 92여 퍼센트의 상위어가 옳게 추출되었다. When a human recognizes nouns in a sentence, s/he associates them with the hyper concepts of nouns. For computer to simulate the human''s word recognition, it should build the knowledge base(WordNet) for the hyper concepts of words. Until now, works for the WordNet haven''t been performed in Korea, because they need lots of human efforts and time. But, as the power of computer is radically improved and common MRD becomes available, it is more feasible to automatically construct the WordNet. This paper proposes the method that automatically builds the WordNet of Korean nouns by using the description of nouns in Korean MRD, and it proposes the rules for extracting the hyper concepts(hypernyms) by analyzing structural characteristics of Korean. The rules effect such characteristics as a headword lies on the rear part of sentences and the descriptive sentences of nouns have special structure. In addition, the WordNet prototype of Korean Nouns is developed, which is made by combining the hypernyms produced by the rules mentioned above. It extracts the hypernyms of about 2,500 sample words, and the result shows that about 92 percents of hypernyms are correct.

단일어 워드넷을 넘어 다국어 워드넷으로 - Asian WordNet과 Global WordNet Grid를 중심으로 -

윤애선 한국일본어문학회 2010 日本語文學 Vol.46 No.-

The Princeton WordNet (PWN) began to be developed about 30 years ago. A variety of word nets were constructed ever since using different representation types and different building methods. Among them, PWN became the most productive reference model derivating more than 50 WordNets over 40 languages, and it turns to its 2nd era for realizing multilinguality. This paper is a critical essay on WordNets, i.e. PWN-type word nets. It discuses the state-of-the-art of WordNets and presents 2 multilingual WordNet models: Asian WordNet and Global WordNet Grid.

한국어 WordNet의 분석과 방향

金權陽 慶一大學校 1999 論文集 Vol.16 No.6

This paper presents the methodology and technology for the automatic construction of a Korean WordNet from the preexisting lexical resources. The English WordNet is used in this methodology as a backbone for Korean Wordnet. And an automatic and complementary technique for linking Korean words collected from Korean monolingual dictionary to English WordNet synsets based on hypernym which was extracted from the dictionary definition.

以 Princeton WordNet 爲通用語言的 韓語詞匯語義網 KorLex 的特性及應用

尹愛善,權爀喆 경성대학교 한국한자연구소 2020 한자연구 Vol.0 No.26

The paper introduces KorLex, Korean WordNet, which uses Princeton WordNet (PWN) as a reference model as well as a pivot that provides KorLex with the multilingual interface. Sub-section 2.1 describes the background for which we intended to build KorLex by ourselves, and the motivations for which we selected PWN as a reference model among other wordnets. Sub-sections 2.2 and 2.3 deal with the semantic features that share both PWN and KorLex, and the linguistic features that we attach to KorLex in order to improve Korean Language Processing (KLP). Section 3 presents two representative applications of KorLex in the field of Natural Language Processing: (1) in KLP environment, <Korean Spell/Grammar Checker (KSGC)> that we have developed for the last 30 years, and for which we decided to elaborate KorLex version 1.5 and to attach the sophisticate information of Korean language to the version 2.0; (2) in multilingual environment, <Korean-Korean_Sign_Language Machine Translation (K2KSL MT)>, which would not be successfully developed without the hierarchical semantic structure of KorLex as well as PWN, since the hierarchy enables K2KSL MT to solve logically the notorious ‘data sparseness (= lack of lexicon)’ problem that KSL encounters during the translation process, like in other bilingual or multilingual MT systems.

How to generate creative ideas for innovation: a hybrid approach of WordNet and morphological analysis

Geum, Y.,Park, Y. American Elsevier 2016 TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE Vol.111 No.-

A creative ideation process occupies a substantial part of the innovation process. Among many techniques for ideation, morphology analysis has been employed as a prevalent method, whose success is critically affected by its dimensions and values. Despite the gravity of determining dimensions and values, previous literature has been simply subject to manual construction by some experts, which leads to significant subjectivity and bias in morphology building. For this reason, an analytic and objective way of morphology building is highly required. In response, this paper suggests a new way of morphology building to enhance creative ideation using WordNet. WordNet is a large lexical database of English, which provides a hierarchical network dictionary of words. WordNet's hierarchical relationship characteristic fits morphology analysis as its nature comes from a hierarchical structure of dimensions and values. The use of WordNet can be an excellent remedy for morphology building by employing two types of relationships: meronym/holonym for dimension construction and hyponym/ hypernym for value construction. Since dimension construction extends the contents of horizontal axis of morphology, it is called horizontal extension. Similarly, value construction extends the contents of vertical axis of morphology, thus it is referred to as vertical extension of morphology.

Document Classification Using N-gram and Word Semantic Similarity

Mei-ying Ren,Sinjae Kang 보안공학연구지원센터 2015 International Journal of u- and e- Service, Scienc Vol.8 No.8

This paper mainly conducted two series of experiments. One is investigation between language dependent and language independent features. Bi-grams in Korean experiments and uni-grams in Chinese contributed most as basic features. And another one is utilization of Korean WordNet to improve the performance of Korean document classification. Korean WordNet is a Korean Lexical Semantic Network. Language independent features seem can lead better performance and stable. The performance of Korean text classification was improved by using Korean WordNet.

정보검색 활용을 위한 다국어 데이터베이스의 ILI(Inter-Lingual-Index) 방법론 연구

오장근(Jang Geun Oh) 언어과학회 2004 언어과학연구 Vol.29 No.-

EuroWordNet is an EC-funded project that aims to build a multilingual database consisting of wordnets in several European languages. In this paper we will discuss in detail the multilingual design of the database and the ways in which it should give access to the resources to make this type of comparison possible. The structure of this paper is as follows: In section 2 we will compare different multilingual design options for our database, and motivate our choice for the so-called Inter-Lingual-Index(ILI). This ILI is an unstructured list of concepts that functions only as a fund for interlinking word meanings across languages. We will then further explain the design and the way in which the equivalence relations are expressed. In section 2.3.2 we will discuss the different types of mismatches that can occur across the wordnets, and the way in which they can be compared in the database to extract the most important cases of mismatch. Finally, in section 3 we describe how we improve the ILI (which is mainly based on WordNet1.5 synsets) to get a more consistent matching across the wordnets. Due to differences in the sense-differentiation across resources, many equivalent synsets may not be linked at all. By extending the ILI with coarser synsets that relate several, more specific meanings, we can improve the matching in an elegant and modular way.

WordNet기반의 형식개념분석기법을 이용한 사용자태그 분류체계의 구축

황석형(Suk-Hyung Hwang) 한국컴퓨터정보학회 2013 韓國컴퓨터情報學會論文誌 Vol.18 No.10

본 논문에서는, 어휘정보를 체계화한 워드넷(WordNet)을 토대로 형식개념분석기법(Formal Concept Analysis)을 사용하여 폭소노미 사용자들의 태그데이터를 분석하여 사용자태그의 분류체계를 구축하기 위한 기법을 제안하였다. 또한, 제안된 기법을 지원하기 위한 도구(TagLighter)의 개발에 대하여 설명하고, 그 유용성을 확인하기 위하여 Bibsonomy.org의 사용자 태그데이터를 대상으로 실시한 실험결과를 기술하였다. TagLighter에 의해 구축된 사용자태그 분류계층구조는 사용자태그에 대한 보다 상세한 이해를 제공하기 때문에, 폭소노미기반 시스템에서의 정보검색과 데이터 분석에 유용하다. 본 논문의 연구결과는, 폭소노미기반의 웹서비스와 소셀네트워크시스템, 시맨틱웹 어플리케이션 등을 대상으로 하는 웹데이터 마이닝분야에 응용할 수 있다. In this paper, we propose a novel approach to construction of classification hierarchies for user tags of folksonomies, using WordNet-based Formal Concept Analysis tool, called TagLighter, which is developed on this research. Finally, to give evidence of the usefulness of this approach in practice, we describe some experiments on user tag data of Bibsonomy.org site. The classification hierarchies of user tags constructed by our approach allow us to gain a better and further understanding and insight in tagged data during information retrieval and data analysis on the folksonomy-based systems. We expect that the proposed approach can be used in the fields of web data mining for folksonomy-based web services, social networking systems and semantic web applications.

문서범주화 성능 향상을 위한 의미기반 자질확장에 관한 연구

정은경 한국정보관리학회 2009 정보관리학회지 Vol.26 No.3

Identifying optimal feature sets in Text Categorization(TC) is crucial in terms of improving the effectiveness. In this study, experiments on feature expansion were conducted using author provided keyword sets and article titles from typical scientific journal articles. The tool used for expanding feature sets is WordNet, a lexical database for English words. Given a data set and a lexical tool, this study presented that feature expansion with synonymous relationship was significantly effective on improving the results of TC. The experiment results pointed out that when expanding feature sets with synonyms using on classifier names, the effectiveness of TC was considerably improved regardless of word sense disambiguation. 기계학습 기반 문서범주화 기법에 있어서 최적의 자질을 구성하는 것이 성능향상에 있어서 중요하다. 본 연구는 학술지 수록 논문의 필수적 구성요소인 저자 제공 키워드와 논문제목을 대상으로 자질확장에 관한 실험을 수행하였다. 자질확장은 기본적으로 선정된 자질에 기반하여 WordNet과 같은 의미기반 사전 도구를 활용하는 것이 일반적이다. 본 연구는 키워드와 논문제목을 대상으로 WordNet 동의어 관계 용어를 활용하여 자질확장을 수행하였으며, 실험 결과 문서범주화 성능이 자질확장을 적용하지 않은 결과와 비교하여 월등히 향상됨을 보여주었다. 이러한 성능향상에 긍정적인 영향을 미치는 요소로 파악된 것은 정제된 자질 기반 및 분류어 기준의 동의어 자질확장이다. 이때 용어의 중의성 해소 적용과 비적용 모두 성능향상에 영향을 미친 것으로 파악되었다. 본 연구의 결과로 키워드와 논문제목을 활용한 분류어 기준 동의어 자질 확장은 문서 범주화 성능향상에 긍정적인 요소라는 것을 제시하였다.

Word2Vec과 WordNet 기반 불확실성 단어 간의 네트워크 분석에 관한 연구

허고은 한국문헌정보학회 2019 한국문헌정보학회지 Vol.53 No.3

과학에서 지식의 불확실성은 명제가 현재 상태로는 참도 거짓도 아닌 불확실한 상태를 의미한다. 기존의 연구들은 학술 문헌에 표현된 명제를 분석하여 불확실성을 의미하는 단어를 수동적으로 구축하고 구축한 코퍼스를 대상으로 규칙 기반, 기계 학습 기반의 성능평가를 수행해왔다. 불확실성 단어 구축의 중요성은 인지하고 있지만 단어의 의미를 분석하여 자동적으로 확장하고자 하는 시도들은 부족했다. 한편, 계량정보학이나 텍스트 마이닝 기법을 이용하여 네트워크의 구조를 파악하는 연구들은 다양한 학문분야에서 지적 구조와 관계성을 파악하기 위한 방법으로 널리 활용되고 있다. 따라서, 본 연구에서는 기존의 불확실성 단어를 대상으로 Word2Vec을 적용하여 의미적 관계성을 분석하였고, 영어 어휘 데이터베이스이자 시소러스인 WordNet을 적용하여 불확실성 단어와 연결된 상위어, 하위어 관계와 동의어 기반 네트워크 분석을 수행하였다. 이를 통해 불확실성 단어의 의미적, 어휘적 관계성을 구조적으로 파악하였으며, 향후 불확실성 단어의 자동 구축의 확장 가능성을 제시하였다. Uncertainty in scientific knowledge means an uncertain state where propositions are neither true or false at present. The existing studies have analyzed the propositions written in the academic literature, and have conducted the performance evaluation based on the rule based and machine learning based approaches by using the corpus. Although they recognized that the importance of word construction, there are insufficient attempts to expand the word by analyzing the meaning of uncertainty words. On the other hand, studies for analyzing the structure of networks by using bibliometrics and text mining techniques are widely used as methods for understanding intellectual structure and relationship in various disciplines. Therefore, in this study, semantic relations were analyzed by applying Word2Vec to existing uncertainty words. In addition, WordNet, which is an English vocabulary database and thesaurus, was applied to perform a network analysis based on hypernyms, hyponyms, and synonyms relations linked to uncertainty words. The semantic and lexical relationships of uncertainty words were structurally identified. As a result, we identified the possibility of automatically expanding uncertainty words.