• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.542-549
• /
• 2017

Sequence-to-sequence models and similar pointer networks suffer from performance degradation when an input is composed of multiple sentences or when the length of the input sentence is long. To solve this problem, this paper proposes a hierarchical pointer network model that uses both the word level and sentence level information to encode input sequences composed of several sentences at the word level and sentence level. We propose a hierarchical pointer network based coreference resolution that performs a coreference resolution for all mentions. The experimental results show that the proposed model has a precision of 87.07%, recall of 65.39% and CoNLL F1 74.61%, which is an improvement of 21.83% compared to an existing rule-based model.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.247-251
• /
• 2018

상호참조해결은 자연언어 문서 내에서 등장하는 명사구 언급(mention)과 이에 선행하는 명사구 언급을 찾아 같은 개체인지 정의하는 문제이다. 특히, 지식베이스 확장에 있어 상호참조해결은 언급 후보에 대해 선행하는 개체의 언급이 있는지 판단해 지식트리플 획득에 도움을 준다. 영어권 상호참조해결에서는 F1 score 73%를 웃도는 좋은 성능을 내고 있으나, 평균 정밀도가 80%로 지식트리플 추출에 적용하기에는 무리가 있다. 따라서 본 논문에서는 한국어 문서에 대해 영어권 상호참조해결 모델에서 사용되었던 최신 모델인 Bi-LSTM 기반의 딥 러닝 기술을 구현하고 이에 더해 언급 후보 목록을 만들어 개체명 유형과 경계를 적용하였으며 품사형태를 붙인 토큰을 사용하였다. 실험 결과, 문자 임베딩(Character Embedding) 값을 사용한 경우 CoNLL F1-Score 63.25%를 기록하였고, 85.67%의 정밀도를 보였으며, 같은 모델에 문자 임베딩을 사용하지 않은 경우 CoNLL F1-Score 67.92%와 평균 정밀도 77.71%를 보였다.

• Journal of Fisheries and Marine Sciences Education
• /
• v.16 no.1
• /
• pp.110-123
• /
• 2004

Five Islands in the West Sea of Korea (Baekryeong-do, Daecheong-do, Socheong-do, Yeonpyeong-do, and Woo-do) are located very close to the North Korea's coast and all of them are under the jurisdiction of South Korea. The North and South Korean naval vessels clashed twice in the West Sea of Korea on June 15, 1999 and on June 29, 2002. These incidents were resulted from conflicts over the validity of the Northern Limit Line(NLL) and the appropriate maritime boundary between the two Koreas. From the viewpoint of South Korea, the North Limit Line is a lawful Maritime Military Demarcation Line under the Korean Military Armistice Agreement and it must be maintained as a maritime boundary between two Koreas until being substituted by a peace treaty. In conclusion, the maritime boundary between two Koreas cannot be settled easily by the principles of the International Law of the Sea at present.

• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.767-783
• /
• 2013

Generalized Method of Moment(GMM) is a popular estimation method to estimate model parameters in empirical financial studies. GMM is frequently applied to estimate diffusion models that are basic techniques of modern financial engineering. However, recent research showed that GMM had poor properties to estimate the parameters that pertain to the diffusion coefficient in diffusion models. This research corrects the weakness of GMM and suggests alternatives to improve the statistical properties of GMM estimators. In this study, a simulation method is adopted to compare estimation methods. Out of compared alternatives, NGMM-Y, a version of improved GMM that adopts the NLL idea of Shoji and Ozaki (1998), showed the best properties. Especially NGMM-Y estimator is superior to other versions of GMM estimators for the estimation of diffusion coefficient parameters.

• Korean Journal of Crystallography
• /
• v.5 no.2
• /
• pp.78-84
• /
• 1994

The crystal structure of N-11-(benzotriazol-1-yl)butyl]-P-nitroaniline ( C16H17N502) has been determinedfromsingle crystal x-ray diffractionstudy:C16H17N502 monoclinic, P21/n, a=17542(2)A, b=10.755(3)A, c=8.891(1)A, β=104.58(1)˚, V=1623.4(5)A3, 7=293(2)K, Z=4, Cuka(A = 1.5418A) , The molecular structure was solved was by direct meshed refined by full-matrix least squares to a final R =0.0411 for 2248 unique observed [F≥4o(p) ] reflections and 255 Parameters. The crystal structure is stabilized by intermolecular N (11) -Hl 1 (Nl 1) ‥‥N (3) hydrogen bond with N(11) ‥‥ N(3) =3.136(2)A and N(11)-Hll(Nll)‥‥N(3) =164.1(15) ˚.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.992-1005
• /
• 2014

Coreference resolution finds all expressions that refer to the same entity in a document. Coreference resolution is important for information extraction, document classification, document summary, and question answering system. In this paper, we adapt Stanford's Multi-pass sieve system, the one of the best model of rule based coreference resolution to Korean. In this paper, all noun phrases are considered to mentions. Also, unlike Stanford's Multi-pass sieve system, the dependency parse tree is used for mention extraction, a Korean acronym list is built 'dynamically'. In addition, we propose a method that calculates weights by applying transitive properties of centers of the centering theory when refer Korean pronoun. The experiments show that our system obtains MUC 59.0%, $B_3$ 59.5%, Ceafe 63.5%, and CoNLL(Mean) 60.7%.

• The Journal of the Korea Contents Association
• /
• v.13 no.12
• /
• pp.81-91
• /
• 2013

Social Media has been vitalized according to development of technology, it make the crowd-funding which have a form of new donation culture. The crowd-funding has been known as form that is supported for getting investments of ongoing or new project by much public in area of cultural art. Nowadays it receive attention from the movie content production. There are so many successful case such as , in abroad while it is hard to find distinct case in Korea' the movie content production market. Since the movie <26 years> informed public of 'the crowd-funding', recently was successfully complete first and second fund-raising and third fund-raising is in progress. It is upraised as a representative successful case.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.113-121
• /
• 2018

Position encoding is a method of applying weights according to position of words that appear in a sentence. Pointer networks is a deep learning model that outputs corresponding index with an input sequence. This model can be applied to coreference resolution using attribute. However, the pointer networks has a problem in that its performance is degraded when the length of input sequence is long. To solve this problem, we proposed two contributions to resolve the coreference. First, we applied position encoding and dynamic position encoding to pointer networks. Second, we stack deeply layers of encoder to make high-level abstraction. As results, the position encoding based stacked pointer networks model proposed in this paper had a CoNLL F1 performance of 71.78%, which was improved by 6.01% compared to vanilla pointer networks.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.535-540
• /
• 2016

Coreference resolution is to identify mentions in documents and is to group co-referred mentions in the documents. It is an essential step for natural language processing applications such as information extraction, event tracking, and question-answering. Recently, various coreference resolution models based on ML (machine learning) have been proposed, As well-known, these ML-based models need large training data that are manually annotated with coreferred mention tags. Unfortunately, we cannot find usable open data for learning ML-based models in Korean. Therefore, we propose an efficient coreference resolution model that needs less training data than other ML-based models. The proposed model identifies co-referred mentions using random forests based on sieve-guided features. In the experiments with baseball news articles, the proposed model showed a better CoNLL F1-score of 0.6678 than other ML-based models.

• Strategy21
• /
• s.30
• /
• pp.63-98
• /
• 2012

Northeast Asia has a multi-layered security structure within which major economic and military powers both confront one another and cooperate at the same time. Major regional powers maintain mutually cooperative activities in the economic sphere while competing one another in order to secure a dominant position in the politico-military arena. The multifarious threats, posed by the North Korea's nuclear development, territorial disputes, and maritime demarcation line issues demonstrate that Northeast Asia suffers more from military conflicts and strifes than any other region in the world. Specifically, major maritime security threats include North Korea's nuclear proliferation and missile launching problems as well as military provocations nearby the Northern Limit Line(NLL) as witnessed in the Cheonan naval ship and Yeonpyong incidents. The ROK Navy has been supplementing its firm military readiness posture in consideration of North Korea's threats on the NLL. It has performed superb roles in defending the nation and establishing the Navy advanced and best picked. It also has been conducive to defend the nation from external military threats and invasion, secure the sea lanes of communications, and establish regional stability and world peace. In order to effectively cope with the strategic environment and future warfares, the ROK Navy needs to shift its military structure to one that is more information and technology intensive. In addition, it should consolidate the ROK-US alliance and extend military cooperative measures with neighboring countries in the Asia-Pacific region. Evolved steadily for the last 60 years, the ROK-US alliance format has contributed to peace and security on the Korean peninsula and in the Northeast Asian region. In conclusion, this manuscript contends that the ROK Navy should strive for the establishment of the following: (1) Construction of Jeju Naval Base; (2) Strategic Navy Equipped with War Deterrence Capabilities; (3) Korean-type of System of Systems; (4) Structure, Budget and Human Resources of the Naval Forces Similar to the Advanced Countries; and (5) Strategic Maritime Alliance and Alignment System as well as Domestic Governance Network for the Naval Families.