• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• Journal of KIISE:Software and Applications
• /
• v.32 no.10
• /
• pp.990-1002
• /
• 2005

To generate coherent texts, it is important to produce appropriate pronouns to refer to previously-mentioned things in a discourse. Specifically, we focus on pronominalization by zero pronouns which frequently occur in Korean. This paper investigates zero pronouns in Korean based on the cost-based centering theory, especially focusing on the center transitions of adjacent utterances. In previous centering works, only one type of nominal entity has been considered as the target of pronominalization, even though other entities are frequently pronominalized as zero pronouns. To resolve this problem, and explain the reference phenomena of real texts, four types of nominal entity (Npair, Ninter, Nintra, and Nnon) from centering theory are defined with the concept of inter-, intra-, and pairwise salience. For each entity type, a case study of zero phenomena is performed through analyzing corpus and building a pronominalization model. This study shows that the zero phenomena of entities which have been neglected in previous centering works are explained via the renter transition of the second previous utterance. We also show that in Ninter, Nintra, and Nnon, pronominalization accuracy achieved by complex combination of several types of features is completely or nearly achieved by using the second previous utterance's transition across genres.

• Korean Journal of Computational Design and Engineering
• /
• v.11 no.1
• /
• pp.27-40
• /
• 2006

The exchange of parameterized feature-based CAD models is important for product data sharing among different organizations and automation systems. The role of feature-based modeling is to gonerate the shape of product and capture design intends In a CAD system. A feature is generated by referring to topological entities in a solid. Identifying referenced topological entities of a feature is essential for exchanging feature-based CAD models through a neutral format. If the CAD data contains the modification history in addition to the construction history, a matching mechanism is also required to find the same entity in the new model (post-edit model) corresponding to the entity in the old model (preedit model). This problem is known as the persistent naming problem. There are additional problems arising from the exchange of parameterized feature-based CAD models. Authors have analyzed previous studies with regard to persistent naming and characteristics for the exchange of parameterized feature-based CAD models, and propose a solution to the persistent naming problem. This solution is comprised of two parts: (a) naming of topological entities based on the object spore information (OSI) and secondary name (SN); and (b) name matching under the proposed naming.

• Korean Journal of Environmental Biology
• /
• v.37 no.3
• /
• pp.362-366
• /
• 2019

A marine green algal species (Chlorophyta) was collected from the eastern coast of Korea. It is morphologically characterized by monostromatic thallus, usually undulate and entire margins, cap-like chloroplast and several pyrenoids per cell. In a phylogenetic tree based on molecular data, the Korean alga nests in the same clade as Monostroma alittorale originally described from Japan, as a sister clade of M. grevillei from France. The genetic distance for ITS(Internal Transcribed Spacer) sequences among Monostroma species ranges from 2.3% to 38.2%. The value between the Korean entity and M. alittorale was calculated as 0.01%, considered to be intraspecific divergence. This Korean entity is identified as Monostroma alittorale based on morphological and molecular analyses. This is the first record of M. alittorale in Korea.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1997.10a
• /
• pp.189-196
• /
• 1997

The development of computer integrated systems for structural design requires models to describe and organize information and activities involved in design. An entity-based integrated design model involves a number of product and process entities. Product entities and process entities describe design information and design activities, respectively. One type of relationships among entities is interaction relationships, which describe interdependencies among design information. The interaction relationships can be represented as constraints. Types of constraints include demand constraints, dependency constraints, and interaction constraints. The concepts of representing and processing demand constraints in an entity-based integrated design model are presented.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4A
• /
• pp.528-538
• /
• 2000

Mobile computing system requires both precise identification and secure authentication scheme on remote mobile entities, which is based on the distributed mobile node. In this paper, existing discrete logarithm based $Schnorr^{[7]}$ like entity authentication schemes are improved by the analysis of performance and security on the hi-directional interactive proofs. And $EIGamal^{[14]}$ like efficient authentication schemes are also proposed. Then, these are enhanced with oblivious transfer based mono directional authentication schemes based on trusted third party for applying to the mobile agent based computing systems. Therefore, proposed schemes provide compatible performance and safety on mobile entity authentication processes.

• International Journal of Safety
• /
• v.4 no.2
• /
• pp.12-17
• /
• 2005

This paper aims at the development of an knowledge base for an electrical fire cause diagnosis system using the entity relation database. The relation database which provides a very simple but powerful way of representing data is widely used. The system focused on database construction and cause diagnosis can diagnose the causes of electrical fires easily and efficiently. In order to store and access to the information concerned with electrical fires, the key index items which identify electrical fires uniquely are derived out. The knowledge base consists of a case base which contains information from the past fires and a rule base with rules from expertise. To implement the knowledge base, Access 2000, one of DB development tools under windows environment and Visual Basic 6.0 are used as a DB building tool. For the reasoning technique, a mixed reasoning approach of a case based inference and a rule based inference has been adopted. Knowledge-based reasoning could present the cause of a newly occurred fire to be diagnosed by searching the knowledge base for reasonable matching. The knowledge-based database has not only searching functions with multiple attributes by using the collected various information(such as fire evidence, structure, and weather of a fire scene), but also more improved diagnosis functions which can be easily wed for the electrical fire cause diagnosis system.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1995.02a
• /
• pp.91-96
• /
• 1995

• Journal of Digital Contents Society
• /
• v.8 no.4
• /
• pp.615-622
• /
• 2007

A game engine should have the architecture that can manage various interactions between entities in a game for offering users various game experience. For this purpose, the game engine architecture based on message system is used. But only by this message based system, it is difficult to change game world continuously according to some storylines. The reason of this is event-driven system like message based system is appropriate for processing individual message but is not appropriate for processing more bigger logical work unit. For this purpose this paper proposes the storyline entity. The storyline entity has logical flows for a storyline and is called by engine continuously. By this proposed game engine architecture he or she can maintain free game experience by message based system and can add some progressing of storylines.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.12 no.1
• /
• pp.3-10
• /
• 2002

This paper proposes an ID-based entity-aunthentication and authenticated key exchange protocol with ECC via two-pass communications between two parties who airs registered to the trusted third-party KC in advance. The proposed protocol developed by applying ECDSA and Diffie-Hellman key exchange scheme to the ID-based key distribution scheme over ECC proposed by H. Sakazaki, E. Okamoto and M. Mambo(SOM scheme). The security of this protocol is based on the Elliptic Curve Discrete Logarithm Problem(ECDLP) and the Elliptic Curve Diffie-Hellman Problem(ECDHP). It is strong against unknown key share attack and it provides the perfect forward secrecy, which makes up for the weakness in SOM scheme,