• Journal of KIISE:Software and Applications
• /
• v.36 no.4
• /
• pp.306-319
• /
• 2009

A name is a key feature for distinguishing people, but we often fail to discriminate people because an author may have multiple names or multiple authors may share the same name. Such name ambiguity problems affect the performance of document retrieval, web search and database integration. Especially, in bibliography information, a number of errors may be included since there are different authors with the same name or an author name may be misspelled or represented with an abbreviation. For solving these problems, it is necessary to disambiguate the names inputted into the database. In this paper, we propose a method to solve the name ambiguity by using social networks constructed based on the relations between authors. We evaluated the effectiveness of the proposed system based on DBLP data that offer computer science bibliographic information.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.163-166
• /
• 2018

개체명 연결이란 주어진 문장에 출현한 단어를 위키피디아와 같은 지식 기반 상의 하나의 개체와 연결하여 특정 개체가 무엇인지 식별하여 모호성을 해결하는 작업이다. 본 연구에서는 위키피디아의 링크를 이용하여 개체 표현(Entity mention)과 학습 데이터, 지식 기반을 구축한다. 또한, Mention/Context 쌍의 표현과 Entity 표현의 코사인 유사도를 이용하여 Score를 구하고, 이를 통해 개체명 연결 문제를 랭킹 문제로 변환한다. 개체의 이름과 분류뿐만 아니라 개체의 설명, 개체 임베딩 등의 자질을 이용하여 모델을 확장하고 결과를 비교한다. 확장된 모델의 개체 링킹 성능은 89.63%의 정확도를 보였다.

• The KIPS Transactions:PartB
• /
• v.16B no.3
• /
• pp.225-232
• /
• 2009

Author name disambiguation is essential for improving performance of document indexing, retrieval, and web search. Author name disambiguation resolves the conflict when multiple authors share the same name label. This paper introduces a novel approach which exploits ontologies and WordNet-based category utility for author name disambiguation. Our method utilizes author knowledge in the form of populated ontology that uses various types of properties: titles, abstracts and co-authors of papers and authors' affiliation. Author ontology has been constructed in the artificial intelligence and semantic web areas semi-automatically using OWL API and heuristics. Author name disambiguation determines the correct author from various candidate authors in the populated author ontology. Candidate authors are evaluated using proposed WordNet-based category utility to resolve disambiguation. Category utility is a tradeoff between intra-class similarity and inter-class dissimilarity of author instances, where author instances are described in terms of attribute-value pairs. WordNet-based category utility has been proposed to exploit concept information in WordNet for semantic analysis for disambiguation. Experiments using the WordNet-based category utility increase the number of disambiguation by about 10% compared with that of category utility, and increase the overall amount of accuracy by around 98%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.5
• /
• pp.59-66
• /
• 2006

A Certification Authority issues X.509 public key certificates to bind a public key to a subject. The subject is specified through one or more subject names in the 'subject' or 'subjectAltName' fields of a certificate. In reality, however, there are individuals that have the same or similar names. This ambiguity can be resolved by including a 'permanent identifier' in all certificates issued to the same subject, which is unique across multiple CAs. But, a person's unique identifier is regarded as a sensitive personal data. Such an identifier cannot simply be included as part of the subject field, since its disclosure may lead to misuse. We present a new method for secure and accurate user authentication through the PEPSI included in the standard certificate extension of a X.509 certificate. The PEPSI can be served not only for user authentication but also for the user anonymity without divulging personal information.