• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.491-500
• /
• 2004

This paper presents an ontology construction method using various computational language resources, and an ontology-based word sense disambiguation method. In order to acquire a reasonably practical ontology the Kadokawa thesaurus is extended by inserting additional semantic relations into its hierarchy, which are classified as case relations and other semantic relations. To apply the ontology to disambiguate word senses, we apply the previously-secured dictionary information to select the correct senses of some ambiguous words with high precision, and then use the ontology to disambiguate the remaining ambiguous words. The mutual information between concepts in the ontology was calculated before using the ontology as knowledge for disambiguating word senses. If mutual information is regarded as a weight between ontology concepts, the ontology can be treated as a graph with weighted edges, and then we locate the weighted path from one concept to the other concept. In our practical machine translation system, our word sense disambiguation method achieved a 9% improvement over methods which do not use ontology for Korean translation.

• Industry Promotion Research
• /
• v.5 no.1
• /
• pp.73-87
• /
• 2020

The purpose of this paper was to find examples of a group of interpretations while biased toward the translation of the manuscripts of Myeongnology, and to apply the criteria of the translation of the manuscripts of Myeongnology in accordance with the criteria of SIN(信), DAL(達), and AH(雅) of EOM-BOK. Since the original author's intention should be faithfully reflected, the translation of the original book should be applied to the interpretation required at that time based on the translation corresponding to SIN(信), the translation corresponding to DAL(達) and the AH(雅) translation corresponding to the elegant interpretation. Translation is the most important purpose of implementing equivalence in the intentions of the original author, so the equivalence of the Source language and the Taget language should be observed even in the differences of expression. Up until now, the question of the translation of the nouns has mainly focused on the translation of the stylistic system by focusing on trying to overcome the structural differences of the language. Translation now requires the implementation of semantic equivalence as well as primarily a stylistic approach. This researcher wanted to open a new horizon for the study of classical literature in Myong-hak by presenting a standard for the translation of robes that achieve the intent and equivalence of the original author in the translation of the original text.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.3
• /
• pp.35-44
• /
• 2011

Ontologies are playing an important role in semantic web which is emerging as a next stage of the web revolution because various kinds of metadata are described in ontologies. Correspondingly, many query languages like SPARQL, RDQL etc. have been proposed for querying these ontologies. But users have to know the structures and resource names of ontologies completely to get search results even if they have expertise on complex formal logic and syntax of the query languages. Especially, casual users do not know the resource names and may use different words from resource names when they write their query language. This vocabulary gap problem have to be solved to raise the success rate. In this paper, an approach for translating user's search words to corresponding resource names has been proposed. This approach uses semantic similarity between user created search words and ontology resource names.

• Korean Journal of Computational Design and Engineering
• /
• v.7 no.3
• /
• pp.157-169
• /
• 2002

In the initial stages of ship design, designers represent geometry, arrangement, and dimension of hull structures with 2D geometric primitives such as points, lines, arcs, and drawing symbols. However, these design information(‘2D geometric primitives’) defined in the drawing sheet require more intelligent translation processes by the designers in the next design stages. Thus, the loss of design semantics could be occurred and following design processes could be delayed. In the initial design stages, it is not easy to adopt commercial 3D CAD systems, which have been developed f3r being used in detail and production design stages, because the 3D CAD systems require detailed input for geometry definition. In this study, a semantic product model data structure was proposed, and an initial structural CAD system was developed based on the proposed data structure. Contents(‘product model data and design knowledges’) of the proposed data structure are filled with minimal input of the designers, and then 3D solid model and production material information can be automatically generated as occasion demands. Finally, the applicability of the proposed semantic product model data structure and the developed initial structural CAD system was verified through application to deadweight 300,000ton VLCC(Very Large Crude oil Carrier) product modeling procedure.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.9-15
• /
• 2011

여러 언어로 작성되는 위키피디아의 경우 언어 간에 등록되어 있는 정보의 양과 내용이 달라 언어 간 정보를 상호 추출하고 서로 통합하는 연구에 대한 관심이 증가하고 있다. 특히, 위키피디아의 요약본으로써 의미가 있는 인포박스는 위키피디아 아티클에 존재하는 구조화된 정보 중 가장 근간이 되는 정보로, 본 논문에서는 위키피디아에 존재하는 인포박스를 1)소스 언어 자원으로부터 획득하여 타겟 언어로 번역하고, 2)번역된 결과물과 웹그래프를 이용하여 타겟 언어 데이터에서 획득하는 정보와 결합하는 과정을 통해 자동으로 인포박스를 생성하는 기법에 대하여 설명한다. 웹그래프는 위키피디아에 존재하는 링크 구조를 통해 서로 다른 두 용어간의 관련도를 측정하여 인포박스에 추가될 내용을 파악하는데 사용한다. 본 논문의 기법은 언어 간 인포박스를 생성하는 측면에서, 영어 인포박스 데이터를 입력으로 하여 한국어 인포박스 데이터를 생성하는 방식으로 진행하였다. 평가를 위하여 기존 한국어에 실제 존재하는 인포박스 데이터와 비교 실험하는 방식을 사용하여 평균적으로 40%의 정확률과 83%의 재현율을 나타내었다. 하지만, 기존 한국어에 존재하는 인포박스 데이터의 내용이 인포박스에 포함될 완전한 데이터를 모두 포함했다고 볼 수 없으므로 본 논문에서 제안하는 수행한 실험의 정확률이 상대적으로 낮게 나온 것으로 분석되었다. 실제 사람이 수작업으로 새롭게 생성된 인포박스 데이터의 적합성을 판별한 경우 평균 76%의 정확률과 91%의 재현율을 나타내었다.

• Journal of KIISE
• /
• v.43 no.6
• /
• pp.653-661
• /
• 2016

The existing pattern-based triple generation systems based on distant supervision could be flawed by assumption of distant supervision. For resolving flaw from an excessive assumption, statistics information has been commonly used for measuring confidence of patterns in previous studies. In this study, we proposed a more accurate confidence measure based on semantic similarity between patterns and properties. Unsupervised learning method, word embedding and WordNet-based similarity measures were adopted for learning meaning of words and measuring semantic similarity. For resolving language discordance between patterns and properties, we adopted CCA for aligning bilingual word embedding models and a translation-based approach for a WordNet-based measure. The results of our experiments indicated that the accuracy of triples that are filtered by the semantic similarity-based confidence measure was 16% higher than that of the statistics-based approach. These results suggested that semantic similarity-based confidence measure is more effective than statistics-based approach for generating high quality triples.

• Journal of KIISE:Software and Applications
• /
• v.36 no.1
• /
• pp.70-81
• /
• 2009

Ontology is an explicit specification of concepts and relationships between concepts in an interest domain. As considered as one of typical knowledge representation methods, ontology is applied to various studies such as information extraction, information integration, information sharing, or knowledge management. In IT based industries, ontology is applied to research on information integration and sharing in order to enhance interoperability between enterprises. In supply chains or logistics, several enterprises participate as business partners to plan movements of goods, and control goods and logistics flows. A number of researches on information integration and sharing for the effective and efficient management of logistics or supply chains have been addressed. In this paper, we address an ontology as a knowledge-base for semantic-based integration of logistics information distributed in the logistics flow. Especially, we focus on developing an ontology that enables to represent and translate semantic meaning of EPC data in the EPC Network applied logistics. We present a scenario for tracing products in logistics in order to show the value of our ontology.

• Language and Information
• /
• v.5 no.2
• /
• pp.21-37
• /
• 2001

Pustejovsky (1995) rekindled debate on the dual problems of how to represent lexical meaning and on the information that is to be encoded in a lexicon. For natural language processing such as machine translation, these are important issues. When a lexical-conceptual mismatch occurs in translation of corresponding words from two different languages, the appropriate representation of their meanings is very important. This paper proposes a new formalism for representing lexical entries by first analysing observable mismatches in comparable pairs of nouns, verbs, and adjectives in English and Korean. Inherent mis-interpretations and mis-readings in each pair are identified. Then, concept theories such as those presented by Ganter and Wille (1996) and Priss (1998) are extended in order to reflect the cognitivist view that meaning resides in concept, and also to incorporate the propositions of the so-called ‘multiple inheritance’system. An alternative to the formalism of Pustejovsky (1995) and Pollard & Sag (1994) is then proposed. Finally, representative examples of lexical mismatches are analysed using the new model.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.246-249
• /
• 2015

기계학습 방법에 기반한 자연어 분석은 학습 데이터가 필요하다. 학습 데이터가 구축된 소스 도메인이 아닌 다른 도메인에 적용할 경우 한국어 의미역 인식 기술은 10% 정도 성능 하락이 발생한다. 본 논문은 기존 도메인 적응 기술을 이용하여 도메인이 다르고, 문장의 형태도 다를 경우에 도메인 적응 알고리즘을 적용하여, 질의응답 시스템에서 필요한 질문 문장 의미역 인식을 위해, 소규모의 질문 문장에 대한 학습 데이터 구축만으로도 한국어 질문 문장에 대해 성능을 향상시키기 위한 방법을 제안한다. 한국어 의미역 인식 기술에 prior 모델을 제안한다. 제안하는 방법은 실험결과 소스 도메인 데이터만 사용한 실험보다 9.42, 소스와 타겟 도메인 데이터를 단순 합하여 학습한 경우보다 2.64의 성능향상을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.18-22
• /
• 2015

기계학습 기반의 의미역 인식에서 주로 어휘, 구문 정보가 자질로 주로 쓰이지만, 의미 정보를 분석하는 의미역 인식은 단어의 의미 정보 또한 매우 주요한 정보이다. 그러나, 기존 연구에서는 의미 정보를 활용할 수 있는 방법이 제한되어 있기 때문에, 소수의 연구만 진행되었다. 본 논문에서는 동형이의어 수준의 의미 애매성 해소 기술, 고유 명사에 대한 개체명 인식 기술, 의미 정보에 기반한 필터링, 유의어 사전을 이용한 클러스터 및 기존 프레임 정보를 확장하는 방법을 제안한다. 제안하는 방법은 기존 연구 대비 뉴스 도메인인 Korean Propbank는 3.14, 위키피디아 문서 기반의 WiseQA 평가셋인 GS 3.0에서는 6.57의 성능 향상을 보였다.