• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.223-226
• /
• 2020

엔터티 링킹을 위해서는 엔터티 링킹을 수행 할 후보 엔터티의 정보를 얻어내는 것이 필요하다. 하지만, 엔터티 정보를 획득하기 어려운 경우, 엔터티 링킹을 수행 할 수 없다. 이 논문에서는 이를 해결하기 위해 데이터셋으로부터 엔터티의 가상 엔터티 설명문을 작성하고, 이를 통해 엔터티 링킹을 수행함으로써 엔터티 정보가 없는 환경에서도 2.58%p밖에 성능 하락이 일어나지 않음을 보인다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.20-23
• /
• 2020

개체 연결이란 문서에서 등장한 멘션(Mention)들을 지식 기반(Knowledge Base)상의 하나의 개체에 연결하는 문제를 말한다. 개체 연결은 개체를 찾는 멘션 탐지(mention detection)과정과 인식된 멘션에 대해 중의성을 해결하여 하나의 개체를 찾는 개체 중의성 해결(Entity disambiguation)과정으로 구성된다. 본 논문에서는 개체 정보를 강화하기 위해 wikipedia2vec정보를 결합하여 Entity 정보를 강화하고 문장 내에 모든 개체 정보를 활용하기 위해 집합적 개체를 정의하고 그래프 구조를 표현하기 위해 GNN을 활용하여 기존보다 높은 성능을 이끌어내었다.

• Genomics & Informatics
• /
• v.18 no.2
• /
• pp.15.1-15.6
• /
• 2020

Named entity recognition tools are used to identify mentions of biomedical entities in free text and are essential components of high-quality information retrieval and extraction systems. Without good entity recognition, methods will mislabel searched text and will miss important information or identify spurious text that will frustrate users. Most tools do not capture non-contiguous entities which are separate spans of text that together refer to an entity, e.g., the entity "type 1 diabetes" in the phrase "type 1 and type 2 diabetes." This type is commonly found in biomedical texts, especially in lists, where multiple biomedical entities are named in shortened form to avoid repeating words. Most text annotation systems, that enable users to view and edit entity annotations, do not support non-contiguous entities. Therefore, experts cannot even visualize non-contiguous entities, let alone annotate them to build valuable datasets for machine learning methods. To combat this problem and as part of the BLAH6 hackathon, we extended the TextAE platform to allow visualization and annotation of non-contiguous entities. This enables users to add new subspans to existing entities by selecting additional text. We integrate this new functionality with TextAE's existing editing functionality to allow easy changes to entity annotation and editing of relation annotations involving non-contiguous entities, with importing and exporting to the PubAnnotation format. Finally, we roughly quantify the problem across the entire accessible biomedical literature to highlight that there are a substantial number of non-contiguous entities that appear in lists that would be missed by most text mining systems.

• Journal of Digital Convergence
• /
• v.12 no.12
• /
• pp.351-356
• /
• 2014

Generally, although securing the condition and location of container freights or normal freights, which load a fresh goods, has been a very important issue in the cold-chain system implementations, it has not gotten out of the traditional methods in the related business world yet. To solve this problem, we propose the designing method and architecture which can be used to implement a smart cold-chain monitoring automation systems. The proposed system architecture is based on the oneM2M standards, and it has 3 layers and entities, which can be implemented to S/W and H/W, network services layer and entity, common services layer and entity, application layer and entity. Based on this architecture, we will not only expect an innovative retrenchment of distribution cost, but also automatically secure the freight condition and location.

• Corrosion Science and Technology
• /
• v.17 no.3
• /
• pp.101-108
• /
• 2018

AA7010 is an Al-Zn-Mg-Cu alloy containing Zr, developed as an alternate to traditional AA7075 alloy owing to their high strength combined with better fracture toughness. It is necessary to improve the corrosion resistance and surface properties of the alloy by incorporating plasma electrolytic oxidation (PEO) method. AA7010-T7452 aluminum alloy has been processed through the forging route with multi-stage working operations, and was coated with $10{\mu}m$ thick $Al_2O_3$ ceramic aluminina coating using the plasma electrolytic oxidation (PEO) method. The corrosion, stress corrosion cracking (SCC) and nano-mechanical behaviours were examined by means of potentiodynamic polarization, slow strain rate test (SSRT) and nano-indentation tests. The results indicated that the additional thermomechanical treatment during the forging process caused a fully recrystallized microstructure, which lead to the poor environmental cracking resistance of the alloy in 3.5% NaCl solution, despite the overaging treatment. Although the fabricated PEO coating improved general corrosion resistance, the brittle nature of the coating did not provide any improvement in SCC resistance of the alloy. However, the hardness and elastic modulus of the coating were significantly higher than the base alloy.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.443-458
• /
• 2008

Since Web pages contain a lot of information today, the Web becomes an important resource to extract some information. In this paper, we proposes a set expansion system which can automatically extract named entities from the Web. Overall, the proposed method consists of three steps. First of all, Web pages, which may include many named entities of a domain, are collected by using several seed words of the domain. Then some pattern rules are extracted by using seed words and the collected Web pages, and the named entity candidates are selected through applying the extracted pattern rules into Web pages. To distinguish real named entities, we develop the new mutual importance measurement method which estimates the importance of named entity candidates. We conducted experiments for 3 domains for Korean and for 8 domains for English. As a result, the proposed method obtained 78.72% MAP in Korean and 96.48% MAP in English. In particular, the performances of English domains are better than the results of the Google set.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.229-236
• /
• 2003

Named entity recognition is the process indispensable to question answering and information extraction systems. This paper presents an HMM based named entity (m) recognition method using the construction principles of compound words. In Korean, many named entities can be decomposed into more than one word. Moreover, there are contextual relationships among nouns in an NE, and among an NE and its surrounding words. In this paper, we classify words into a word as an NE in itself, a word in an NE, and/or a word adjacent to an n, and train an HMM based on NE-related word types and parts of speech. Proposed named entity recognition (NER) system uses trigram model of HMM for considering variable length of NEs. However, the trigram model of HMM has a serious data sparseness problem. In order to solve the problem, we use multi-level back-offs. Experimental results show that our NER system can achieve an F-measure of 87.6% in the economic articles.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.9
• /
• pp.419-424
• /
• 2016

Named entity recognition is required to improve the retrieval accuracy of patent documents or similar patents in the claims and patent descriptions. In this paper, we proposed an automatic named entity recognition for patents by using a conditional random field that is one of the best methods in machine learning research. Named entity recognition system has been constructed from the training set of tagged corpus with 660,000 words and 70,000 words are used as a test set for evaluation. The experiment shows that the accuracy is 93.6% and the Kappa coefficient is 0.67 between manual tagging and automatic tagging system. This figure is better than the Kappa coefficient 0.6 for manually tagged results and it shows that automatic named entity tagging system can be used as a practical tagging for patent documents in replacement of a manual tagging.

• Journal of the Korea Society for Simulation
• /
• v.26 no.2
• /
• pp.19-29
• /
• 2017

System Entity Structure/Model Base (SES/MB) enhances organizing model families and storing and reusing model components in the multifaceted system modeling. However, the real world can be described not only an individual system but also a collection of those systems, which is called system of systems (SoS). Because SES/MB has a limitation to simulate the SoS using HLA/RTI, an extended framework is required to simulate it. Therefore, this paper proposes System of Systems Entity Structure/Federate Base (SoSES/FB) for simulation in a distributed environment (HLA/RTI). The proposed method provides the library of federates (FB) and System of System Entity Structure (SoSES) formalism, which represents structural knowledge of a collection of simulators. It also provides a methodology for the development process of distributed simulation. The paper introduces the anti-missile defense simulation using the proposed SoSES/FB.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.17 no.2
• /
• pp.223-234
• /
• 2014

This paper proposes a flexible and highly reusable modeling methodology for a next-generation combat entity which enables joint analysis of performance/engagement effectiveness. According to the scope of the proposed work, the paper is divided into two parts; Part 1 focuses on a conceptual model design, whereas Part 2 proposes detailed model specification and implementation. In Part 1, we, first, classify the combat entity model as combat logic and battlefield function sub-models for joint analysis. Based on the sub-models, we propose two dimensional model partition method, which creates six groups of a single combat entity model by two dimensions: three-activity and two-abstraction. This grouping enables us to reconfigure the combat entity model by sharing the same interface within the group, and the same interface becomes the fundamental basis of the flexible model composition. Furthermore, the proposed method provides a model structure that effectively reflects the real world and maximizes the multi-level reusability of a combat entity model. As a case study, we construct a model design for anti-surface ship warfare. The case study proves enhancement of model reusability in the process of scenario expansion from pattern running to wire guided torpedo operations.