• Proceedings of the Korean Society for Language and Information Conference
• /
• 2005.06a
• /
• pp.71-85
• /
• 2005

To build a Korean wordnet, we translated semi-automatically the English wordnet PWN into Korean verbs. During this process, we found that some of translation errors are related to the arbitrariness of PWN`s sense distinction in regard to the accusativity/inaccusativity of the same verb form in English. This study presents an empirically based method of remodeling the PWN for Korean wordnet and while revising the PWN`s hierarchical structure, it shows the necessity of classifying the Korean passive verbs as semantically autonomous.

• Language and Information
• /
• v.9 no.2
• /
• pp.23-48
• /
• 2005

This study aims to discuss the word sense distinction of Korean middle verbs for restructuring KorLexVerb 1.0. Despite the duality of its meaning and syntactic structure, the word senses of middle verb are not clearly distinguished in current dictionaries. The underspecification causes very often mismatches that a same Korean word sense is used for two different English verb senses. A close examination on the syntactic and semantic properties of middle verb shows us that the word sense distinction and the reconstruction of hierarchical structure are indispensable. Finally, by doing this fine grained word sense distinction, we propose an alternative way of classification and description of the verb polysemy for KorLexVerb 1.0 as well as for dictionary-like language resources.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2005.06a
• /
• pp.1-16
• /
• 2005

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2001.06a
• /
• pp.113-139
• /
• 2001

중간언어 (interlingua, IL) 구축을 지향하는 시각에서 단어의 다의성 (polysemy) 문제를 각종 워드넷의 기술 방식과 용례를 대비하여 논의하고, 센스(어의) 번호를 부착한 세계 워드넷 (Would Wordnet) 데이터베이스를 구상하고, 이 연장 선상에서 (Pustejvsky 식) 생성 어휘 부와 TMR(텍스트의미표상)이론을 가미한 제약기반 통합문법(CUG)으로 IL구축에 다리를 놓고, 이로부터 개별언어 기술로 변환한다.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.92-97
• /
• 2002

의미기반 정보 검색, 자연어 질의 응답, 지식 자동 습득, 담화 처리 등 높은 수준의 자연언어처리 시스템에서 의미처리를 위한 대용량의 지식 베이스가 필요하다. 이러한 지식 베이스 중에서 가장 기본적인 것이 워드넷이다. 이러한 워드넷을 이용함으로써 여러 의미 사이의 의미 유사도를 구할 수 있고, 속성을 물려받을 수 있기 때문에 비슷한 속성을 가진 의미들을 한꺼번에 다루는 데 유용하다. 본 논문에서는 기본 어휘를 바탕으로 기존의 명사 워드넷과 단일어 사전을 이용하여 한국어 동사 워드넷을 구축하는 방법을 제시한다. 본 논문에서 1차 작업을 통하여 구축한 동사 워드넷에는 동사 1,757개에 대한 4,717개의 의미(중복을 포함하면 모두 5,235개의 의미)를 포함하고 있으며 특별히 의미가 많이 편중된 14개의 개념에 속한 571개의 의미를 53개의 세부 개념으로 재분류하여 최종적으로 모두 767개의 계층적 개념으로 구성된 동사 워드넷이 만들어 졌다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.1
• /
• pp.92-108
• /
• 2009

The Princeton WordNet (PWN), which was developed during last 20 years since the mid 80, aimed at representing a mental lexicon inside the human mind. Its potentiality, applicability and portability were more appreciated in the fields of NLP and KE than in cognitive psychology. The semantic and knowledge processing is indispensable in order to obtain useful information using human languages, in the CMC and HCI environment. The PWN is able to provide such NLP-based systems with 'concrete' semantic units and their network. Referenced to the PWN, about 50 wordnets of different languages were developed during last 10 years and they enable a variety of multilingual processing applications. This paper aims at describing PWN-referenced Korean Wordnet, KorLex 1.5, which was developed from 2004 to 2007, and which contains currently about 130,000 synsets and 150,000 word senses for nouns, verbs, adjectives, adverbs, and classifiers.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.290-295
• /
• 2002

Since thesaurus is used as a knowledge resource in many natural language processing systems, it is very useful and necessary for the high quality systems, especially for dealing with semantics. In this paper, we introduce a semi-automatic method for the construction of Korean noun semantic hierarchy by utilizing a monolingual MRD and an existing thesaurus.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.92-96
• /
• 2009

인간이 가진 개념을 지식베이스화하려는 시도 중 하나로 의미망이 구축되고 있다. 한국어를 대상으로 한 어휘 의미망 중 프린스턴 대학의 WordNet을 대역한 KorLex는 1,2단계에서 한국어 어휘의미의 특성을 반영하여 개념 및 의미구조를 재구조화하고 있다. 그러나 현재 KorLex의 동의어 집합을 구성하는 어휘 의미에는 논항정보를 따로 구성할 수 없었다. 본 연구는 세종 전자 사전 격틀정보내의 선택제약조건(selectional restriction)으로 사용되고 있는 의미 부류와 KorLex의 명사 어휘 의미망을 자동 맵핑하는 방안을 제안함으로써 KorLex에서 세종 전자 사전 격틀정보를 활용할 수 있는 가능성을 제공한다.

• Journal of IKEEE
• /
• v.14 no.4
• /
• pp.305-311
• /
• 2010

Most recent web search engines perform effective keyword-based multimedia contents retrieval by investigating keywords associated with multimedia contents on the Web and comparing them with query keywords. On the other hand, most music and compilation albums provide professional artwork as cover art that will be displayed when the music is played. If the cover art is not available, then the music player just displays some dummy or random images, but this has been a source of dissatisfaction. In this paper, in order to automatically create cover art that is matched with music contents, we propose a music album cover art creation scheme based on music contents analysis and result synthesis. We first (i) analyze music contents and their lyrics and extract representative keywords, (ii) expand the keywords using WordNet and generate various queries, (iii) retrieve related images from the Web using those queries, and finally (iv) synthesize them according to the user preference for album cover art. To show the effectiveness of our scheme, we developed a prototype system and reported some results.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.493-501
• /
• 2022

This paper is a study on context-sensitive spelling error correction and uses the Korean WordNet (KorLex)[1] that defines the relationship between words as a graph to improve the performance of the correction[2] based on the vector information of the word embedded in the correction technique. The Korean WordNet replaced WordNet[3] developed at Princeton University in the United States and was additionally constructed for Korean. In order to learn a semantic network in graph form or to use it for learned vector information, it is necessary to transform it into a vector form by embedding learning. For transformation, we list the nodes (limited number) in a line format like a sentence in a graph in the form of a network before the training input. One of the learning techniques that use this strategy is Deepwalk[4]. DeepWalk is used to learn graphs between words in the Korean WordNet. The graph embedding information is used in concatenation with the word vector information of the learned language model for correction, and the final correction word is determined by the cosine distance value between the vectors. In this paper, In order to test whether the information of graph embedding affects the improvement of the performance of context- sensitive spelling error correction, a confused word pair was constructed and tested from the perspective of Word Sense Disambiguation(WSD). In the experimental results, the average correction performance of all confused word pairs was improved by 2.24% compared to the baseline correction performance.