• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.451-453
• /
• 2005

본 논문에서는 한국어에 있어 '에, 로'를 격표지로 하는 부사격에 대한 의미역 결정 모델에 대해 다루고 있다. 의미역 결정은 의미 분석의 핵심 과정 중 하나이고 자연언어처리에서 해결해야 할 중요한 문제이다. 본 논문은 기존 연구와 언어학 논저를 참고해서 의미역 결정에 유용한 자질들을 정리하였고 SVM을 이용하여 의미역 결정 모델을 구축하였다. 또한 기존 연구와 차별적으로 기능동사 구문의 처리와 지배소 개념의 유사도 보정 방법을 사용하여 보다 견고한 모델을 만들 수 있었다. 성능 평가 결과 개념(Concept)만을 사용한 기본 모델에 비해서 평균 $9\%$의 정확률 향상을 보였다.

• Journal of Environmental Science International
• /
• v.28 no.11
• /
• pp.951-958
• /
• 2019

Seoullo7017, an elevated linear park, was created to redevelop obsolete road infrastructure as public space, which provides unique landscapes. This study was aimed to evaluate and suggest proper planting design for improving psychological benefits in Seoullo7017. Field survey and simulation experiment were carried out to investigate the user's perception on the landscapes. Many users had negative feelings of the present landscapes in Seoullo7017, due to concrete pavement and simple planting design using big concrete pots. Landscape simulation experiment showed this perception could change depending on planting design. In especial, herb species played an important role in improving the quality of landscape in a linear park and providing positive feelings such as refreshment, warmth and naturalness. This study suggested that planting design in a linear space needs to be focused rather on the planting style and species than the volume of greens.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.9-15
• /
• 2018

Policy polls, which investigate the degree of support that the policy has for policy implementation, play an important role in making decisions. As the number of Internet users increases, the public is actively commenting on their policy news stories. Current policy polls tend to rely heavily on phone and offline surveys. Collecting and analyzing policy articles is useful in policy surveys. In this study, we propose a method of analyzing comments using deep learning technology showing outstanding performance in various fields. In particular, we designed various models based on the recurrent neural network (RNN) which is suitable for sequential data and compared the performance with the support vector machine (SVM), which is a traditional machine learning model. For all test sets, the SVM model show an accuracy of 0.73 and the RNN model have an accuracy of 0.83.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.931-956
• /
• 2019

Documents contain information that can be used for various applications, such as question answering (QA) system, information retrieval (IR) system, and recommendation system. To use the information, it is necessary to develop a method of extracting such information from the documents written in a form of natural language. There are several kinds of the information (e.g., temporal information, spatial information, semantic role information), where different kinds of information will be extracted with different methods. In this paper, the existing studies about the methods of extracting the temporal information are reported and several related issues are discussed. The issues are about the task boundary of the temporal information extraction, the history of the annotation languages and shared tasks, the research issues, the applications using the temporal information, and evaluation metrics. Although the history of the tasks of temporal information extraction is not long, there have been many studies that tried various methods. This paper gives which approach is known to be the better way of extracting a particular part of the temporal information, and also provides a future research direction.

• Journal of Information Technology Applications and Management
• /
• v.26 no.1
• /
• pp.65-75
• /
• 2019

As the use of semantic web based on XML increases in the field of data management, a lot of studies to extract useful information from the data stored in ontology have been tried based on association rule mining. Ontology data is advantageous in that data can be freely expressed because it has a flexible and scalable structure unlike a conventional database having a predefined structure. On the contrary, it is difficult to find frequent patterns in a uniformized analysis method. The goal of this study is to provide a basis for extracting useful knowledge from ontology by searching for frequently occurring subgraph patterns by applying transaction-based graph mining techniques to ontology schema graph data and instance graph data constituting ontology. In order to overcome the structural limitations of the existing ontology mining, the frequent pattern search methodology in this study uses the methodology used in graph mining to apply the frequent pattern in the graph data structure to the ontology by applying iterative node chunking method. Our suggested methodology will play an important role in knowledge extraction.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.334-338
• /
• 2022

In visual simultaneous localization and mapping (vSLAM), the correct recognition of a place benefits in relocalization and improved map accuracy. However, its performance is significantly affected by the environmental conditions such as variation in light, viewpoints, seasons, and presence of dynamic objects. This research addresses the problem of feature occlusion caused by interference of dynamic objects leading to the poor performance of visual place recognition algorithm. To overcome the aforementioned problem, this research analyzes the role of scene semantics in correct detection of a place in challenging environments and presents a semantics aided visual place recognition method. Semantics being invariant to viewpoint changes and dynamic environment can improve the overall performance of the place matching method. The proposed method is evaluated on the two benchmark datasets with dynamic environment and seasonal changes. Experimental results show the improved performance of the visual place recognition method for vSLAM.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.1-4
• /
• 2022

As computers can express and utilize information in a semantic dimension different from the real world, humans have opened the door to the digital world and have played a pivotal role in the transformation of the human habitual environment. Using metaverse, it can be possible to predict concepts such as virtual currency, artificial intelligence, and virtual reality, which have now become possible for practical systemic visualization. In order to implement the metaverse in the realm of technology, it requires not only a multifaceted discussion on the platform, but also research on an architect that can include the intrinsic complexity of the metaverse. In this paper, we discuss the architecture for an open metaverse platform based on convergence wrapping that can converge various contents into one space, and propose a comprehensive platform design.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.199-202
• /
• 2021

의미역 결정은 입력된 문장 내 어절간의 의미 관계를 예측하기 위한 자연어처리 태스크이며, 핵심 서술어에 따라 상이한 의미역 집합들이 존재한다. 기존의 연구는 문장 내의 서술어의 개수만큼 입력 문장을 확장해 순차 태깅 문제로 접근한다. 본 연구에서는 확장된 입력 문장에 대해 구문 분석을 수행 후 추출된 문장 구조 정보를 의미역 결정 모델의 자질로 사용한다. 이를 위해 기존에 학습된 구문 분석 모델의 파라미터를 전이하여 논항의 위치를 예측한 후 파이프라인을 통해 의미역 결정 모델을 학습시킨다. ALBERT 사전학습 모델을 통해 입력 토큰의 표현을 얻은 후, 논항의 위치에 대응되는 표현을 따로 추상화하기 위한 계층형 트랜스포머 인코더 레이어 구조를 추가했다. 실험결과 Korean Propbank 데이터에 대해 F1 85.59의 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.172-175
• /
• 2020

최근 자연어처리는 대용량 코퍼스를 이용하여 언어 모델을 사전 학습하고 fine-tuning을 적용함으로 다양한 태스크에서 최고 성능을 갱신하고 있다. BERT기반의 언어 모델들은 양방향의 Transformer만 모델링 되어 있지만 BART는 양방향의 Transformer와 Auto-Regressive Transformer가 결합되어 사전학습을 진행하는 모델로 본 논문에서는 540MB의 코퍼스를 이용해 한국어 BART 모델을 학습 시키고 여러 한국어 자연어처리 태스크에 적용하여 성능 향상 있음을 보였다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.189-195
• /
• 2024

The issue "Exploring Social Media and Other Crucial Success Elements of Attitude towards Politics and Intention for Voting in Pakistan" is a huge study embracing more issues. The politics of Pakistan is basically the politics of semantic groups. Pakistan is a multilingual state more than six languages. There are 245 religious parties in Pakistan, as elaborated by the Daily Times research. The use of social media sites in Pakistan peaked to its maximum after announcement of election schedule by the Election Commission of Pakistan in March 22, 2013. Most of the political parties used it for the recent elections in Pakistan to promote their agenda and attract country's 80 million registered electors. This study was aiming to investigate the role of social media and other critical variables in the attitude towards politics and intention for voting.