• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.533-536
• /
• 2019

의존 구문 분석은 문장 구성 성분 간의 의존 관계를 분석하는 태스크로, 자연어 이해의 대표적인 과제 중 하나이다. 본 논문에서는 한국어 의존 구문 분석의 성능 향상을 위해 Deep Bi-Affine Network와 Left to Right Dependency Parser를 적용하고, 새롭게 한국어의 언어적 특징을 반영한 Right to Left Dependency Parser 모델을 제안한다. 3개의 의존 구문 분석 모델에 단어 표현을 생성하는 방법으로 ELMo, BERT 임베딩 방법을 적용하고 여러 종류의 모델을 앙상블하여 세종 의존 구문 분석 데이터에 대해 UAS 94.50, LAS 92.46 성능을 얻을 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2476-2495
• /
• 2021

Model-based software architecture verification and test scenarios generation are becoming more and more important in the software industry. Based on the existing temporal graph grammar, this paper proposes a new formalization method of the context-sensitive graph grammar for aiming at UML activity diagrams, which is called the UML Activity Graph Grammar, or UAGG. In the UAGG, there are new definitions and parsing algorithms. The proposed mechanisms are able to not only check the structural correctness of the UML activity diagram but also automatically generate the test scenario according to user constraints. Finally, a case study is discussed to illustrate how the UAGG and its algorithms work.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.552-557
• /
• 2017

Wire, wireless digital broadcasting has sharply expanded with the birth of high definition TV since 2010, the use of duplex contents as well as simplex contents has rapidly increased. Currently, our satellite communications system adopted DVB by European digital broadcasting standardization organization as a standard of domestic data broadcasting, the method how to use selective contents has been studied variously according to the development of IPTV. Digital broadcasting utilizes the method using Transport Stream Packet(TSP) by the way of multiplexing of information in order to send multimedia information such as video, audio and data of MPEG-2, this streams include detail information on TV guide and program as well as video and audio information. In order to understand these data broadcasting system, this study realized TS analyzer that divides transport stream (TS) by packet in Linux environment, analyzes and prints by function, it can help the understanding of TS, the enhancement of stream parsing ability.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1983.02a
• /
• pp.59-76
• /
• 1983

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1994.02a
• /
• pp.63-72
• /
• 1994

Dependency Grammar has been used by Iinguists as the basis of the syntactic components of their grammar formalisms. It has also been used in natural langauge parsing. In China, attempts have been made to use this grammar formalism to parse Chinese sentences using corpus based techniques. This paper reviews the properties of Dependency Grammar as embodied in four axioms for the well-formedness conditions for dependency structures. It is shown that allowing mul tiple governors as done by some followers of this formalism is unnecessary. The practice of augmenting Dependency Grammar with functional labels is discussed in the light of building functional structures when the sentence is parsed. This will also facilitate semantic interpretion.retion.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.608-610
• /
• 2018

한국어 의존 구문 분석(Dependency Parsing)은 문장 어절의 중심어(head)와 수식어(modifier)의 의존관계를 표현하는 자연어 분석 방법이다. 최근에는 이러한 의존 관계를 표현하기 위해 주의 집중 메커니즘(Attention Mechanism)과 LSTM(Long Short Term Memory)을 결합한 모델들이 높은 성능을 보이고 있다. 본 논문에서는 개선된 Biaffine Attention 의존 구문 분석 모델을 제안한다. 제안된 모델은 기존의 Biaffine Attention에서 의존성과 의존 관계를 결정하는 방법을 개선하였고, 한국어 의존 구문 분석을 위한 입력 열의 형태소 표상을 확장함으로써 기존의 모델보다 UAS(Unlabeled Attachment Score)가 0.15%p 더 높은 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.144-148
• /
• 2019

비유창성(disfluency)은 문어와 같이 정연한 구조로 말하지 못하는 현상 전반을 지칭한다. 이는 구어에서 보편적으로 발생하는 현상으로 구어 의존 구문 분석의 난이도를 상향시키는 요인이다. 본 연구에서는 비유창성 요소 유형을 담화 표지, 수정 표현, 반복 표현, 삽입 표현으로 분류하였다. 또한 유형별 비유창성 요소를 실제 말뭉치에서 어떻게 구문 주석할 것인지를 제안한다. 이와 같은 구어 데이터 처리 방식은 대화시스템 등 구어를 처리해야 하는 도메인에서의 자연언어이해 성능 향상에 기여할 것이다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.543-545
• /
• 2019

본 논문은 최신 한국어 의존 구문 분석 모델(Korean dependency parsing model)들과 다양한 앙상블 모델(ensemble model)들을 결합하여 그 성능을 분석한다. 단어 표현은 미리 학습된 워드 임베딩 모델(word embedding model)과 ELMo(Embedding from Language Model), Bert(Bidirectional Encoder Representations from Transformer) 그리고 다양한 추가 자질들을 사용한다. 또한 사용된 의존 구문 분석 모델로는 Stack Pointer Network Model, Deep Biaffine Attention Parser와 Left to Right Pointer Parser를 이용한다. 최종적으로 각 모델의 분석 결과를 앙상블 모델인 Bagging 기법과 XGBoost(Extreme Gradient Boosting) 이용하여 최적의 모델을 제안한다.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.21-29
• /
• 2020

Accurate estimation of human pose relies on backbone method in which its role is to extract feature map. Up to dated, the method of backbone feature extraction is conducted by the plain convolutional neural networks named by CNN and the residual neural networks named by Resnet, both of which have various architectures and performances. The CNN family network such as VGG which is well-known as a multiple stacked hidden layers architecture of deep learning methods, is base and simple while Resnet which is a bottleneck layers architecture yields fewer parameters and outperform. They have achieved inspired results as a backbone network in human pose estimation. However, they were used then followed by different pose estimation networks named by pose parsing module. Therefore, in this paper, we present a comparison between the plain CNN family network (VGG) and bottleneck network (Resnet) as a backbone method in the same pose parsing module. We investigate their performances such as number of parameters, loss score, precision and recall. We experiment them in the bottom-up method of human pose estimation system by adapted the pose parsing module of openpose. Our experimental results show that the backbone method using VGG network outperforms the Resent network with fewer parameter, lower loss score and higher accuracy of precision and recall.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1998.02a
• /
• pp.340-347
• /
• 1998