• ETRI Journal
• /
• v.45 no.1
• /
• pp.93-104
• /
• 2023

Coreference resolution is a task in discourse analysis that links several headwords used in any document object. We suggest pointer networks-based coreference resolution for Korean using multi-task learning (MTL) with an attention mechanism for a hierarchical structure. As Korean is a head-final language, the head can easily be found. Our model learns the distribution by referring to the same entity position and utilizes a pointer network to conduct coreference resolution depending on the input headword. As the input is a document, the input sequence is very long. Thus, the core idea is to learn the word- and sentence-level distributions in parallel with MTL, while using a shared representation to address the long sequence problem. The suggested technique is used to generate word representations for Korean based on contextual information using pre-trained language models for Korean. In the same experimental conditions, our model performed roughly 1.8% better on CoNLL F1 than previous research without hierarchical structure.

• English Language & Literature Teaching
• /
• v.12 no.4
• /
• pp.253-276
• /
• 2006

The purpose of this study is to compare and analyze the aspects of task-based materials in high school English textbooks for first year students in Korea. Based on the theoretical backgrounds for designing communicative tasks and the basic contents of the 7th national curriculum for English, a total of six different qualitative evaluation categories of task-based materials are constructed. The six categories include input data, settings, activity types, language skills, activity themes, and communicative functions. The results of the data analysis showed that the regulations of the 7th national English curriculum, which were aimed at improving the students' communicative abilities, were properly reflected in the materials of task-based activities of all textbooks. On the other hand, a few problems were found in some textbooks: too many individual tasks; being out of proportion in presenting task types and themes; non-systematic introduction of language skills, etc. To conclude, a few suggestions are made to provide some meaningful considerations for the text material developers in order to produce better textbooks in the future: task goals and rationale that encourage the learner's positive motivation; authenticity of input data based on the real-world context; a collaborative learning environment that enhances communicative interaction; a proportional representation of the various activity types including creative problem-solving procedures; systematic introduction of integrated language skills, etc.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.23-32
• /
• 2008

This paper presents a task planning system for a steward robot, which has been developed as an interactive intermediate agent between an end-user and a complex smart home environment called the ISH (Intelligent Sweet Home) at KAIST (Korea Advanced Institute of Science and Technology). The ISH is a large-scale robotic environment with various assistive robots and home appliances for independent living of the elderly and the people with disabilities. In particular, as an approach for achieving human-friendly human-robot interaction, we aim at 'simplification of task commands' by the user. In this sense, a task planning system has been proposed to generate a sequence of actions effectively for coordinating subtasks of the target subsystems from the given high-level task command. Basically, the task planning is performed under the framework of STRIPS (Stanford Research Institute Problem Solver) representation and the split planning method. In addition, we applied a state-partitioning technique to the backward split planning method to reduce computational time. By analyzing the obtained graph, the planning system decomposes an original planning problem into several independent sub-problems, and then, the planning system generates a proper sequence of actions. To show the effectiveness of the proposed system, we deal with a scenario of a planning problem in the ISH.

• MALSORI
• /
• no.53
• /
• pp.75-92
• /
• 2005

Prosody Generation Based on C-ToBI Representation for Text-to-SpeechSeungwon Kim, Yu Zheng, Gary Geunbae Lee, Byeongchang KimProsody modeling is critical in developing text-to-speech (TTS) systems where speech synthesis is used to automatically generate natural speech. In this paper, we present a prosody generation architecture based on Chinese Tone and Break Index (C-ToBI) representation. ToBI is a multi-tier representation system based on linguistic knowledge to transcribe events in an utterance. The TTS system which adopts ToBI as an intermediate representation is known to exhibit higher flexibility, modularity and domain/task portability compared with the direct prosody generation TTS systems. However, the cost of corpus preparation is very expensive for practical-level performance because the ToBI labeled corpus has been manually constructed by many prosody experts and normally requires a large amount of data for accurate statistical prosody modeling. This paper proposes a new method which transcribes the C-ToBI labels automatically in Chinese speech. We model Chinese prosody generation as a classification problem and apply conditional Maximum Entropy (ME) classification to this problem. We empirically verify the usefulness of various natural language and phonology features to make well-integrated features for ME framework.

• Journal of architectural history
• /
• v.26 no.3
• /
• pp.7-18
• /
• 2017

This research focuses on the cadastre and cartographic tradition regarding the representation of Rome that had lasted until the middle of 18th Century. Since the early period of Roman Republic until the early 18th Century, map was considered as a effective medium to record the status of urban facts and also a manifestation of changing perception of reality. These facts allow to diagnose social and conventional changes that had occurred in the field of representation techniques and methodologies derived from diverse intention and objective in elaboration of each map. Cartography also has affinity to architectural drawing as many categories of individuals are involved, clients, researchers, craftsmen, publisher and collectors. Fundamental task of documenting the contemporary physical reality was given to the map, however, as architects had practiced through the drawings, cartographers also reconstruct in subjective way specific buildings and urban aspects according to various needs and demands. As such, philology and imagination play important role as two constitute extreme poles in the evolution of the cadastre. Through analysis of paradigmatic examples in the genealogy of cartography of Rome, it was possible to understand the changing episteme that testify the mentality and custom in the field of visual representation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4510-4526
• /
• 2017

Most available methods of facial gender recognition work well under a constrained situation, but the performances of these methods have decreased significantly when they are implemented under unconstrained environments. In this paper, a method via low-rank and collaborative representation is proposed for facial gender recognition in the wild. Firstly, the low-rank decomposition is applied to the face image to minimize the negative effect caused by various corruptions and dynamical illuminations in an unconstrained environment. And, we employ the collaborative representation to be as the classifier, which using the much weaker $l_2-norm$ sparsity constraint to achieve similar classification results but with significantly lower complexity. The proposed method combines the low-rank and collaborative representation to an organic whole to solve the task of facial gender recognition under unconstrained environments. Extensive experiments on three benchmarks including AR, CAS-PERL and YouTube are conducted to show the effectiveness of the proposed method. Compared with several state-of-the-art algorithms, our method has overwhelming superiority in the aspects of accuracy and robustness.

• Journal of Computing Science and Engineering
• /
• v.12 no.1
• /
• pp.1-11
• /
• 2018

Human activities recognition is a challenging task due to its complexity of human movements and the variety performed by different subjects for the same action. This paper presents a recognition algorithm by using skeleton information generated from depth maps. Concatenating motion features and temporal constraint feature produces feature vector. Reducing dictionary scale proposes an improved fast classifier based on sparse representation. The developed method is shown to be effective by recognizing different activities on the UTD-MHAD dataset. Comparison results indicate superior performance of our method over some existing methods.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.5
• /
• pp.27-34
• /
• 2005

To accomplish various and complex tasks by intelligent robots, improvement is needed not only in mechanical system architecture but also in control system architecture. Hybrid control architecture has been suggested as a mutually complementing architecture of the weak points of a deliberative and a reactive control. This paper addresses a control architecture of robots, and a behavior representation methodology. The suggested control architecture consists of three layers of deliberative, sequencing, and reactive as hybrid control architecture. Multi-layer behavior model is employed to represent desired tasks. 3D simulation will be conducted to verify the applicability of suggested control architecture and behavior representation method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.910-913
• /
• 2021

Successor representation (SR) 은 두뇌 내 해마의 공간 세포가 인지맵을 구성하여 환경을 학습하고, 이를 활용하여 변화하는 환경에서 유연하게 최적 전략을 수립하는 기전을 모사한 강화학습 방법이다. 특히, 학습한 환경 정보를 활용, 환경 구조 안에서 목표가 변화할 때 강인하게 대응하여 일반 model-free 강화학습에 비해 빠르게 보상 변화에 적응하고 최적 전략을 찾는 것으로 알려져 있다. 본 논문에서는 SR 기반 강화학습 알고리즘이 보상의 변화와 더불어 환경 구조, 특히 환경의 상태 천이 확률이 변화하여 보상의 변화를 유발하는 상황에서 어떠한 성능을 보이는 지 확인하였다. 벤치마크 알고리즘으로 SR 의 특성을 목적 기반 강화학습으로 통합한 SR-Dyna 를 사용하였고, 환경 상태 천이 불확실성과 보상 변화가 동시에 나타나는 2-stage 마르코프 의사결정 과제를 실험 환경으로 사용하였다. 시뮬레이션 결과, SR-Dyna 는 환경 내 상태 천이 확률 변화에 따른 보상 변화에는 적절히 대응하지 못하는 결과를 보였다. 본 결과를 통해 두뇌의 강화학습과 알고리즘 강화학습의 차이를 이해하여, 환경 변화에 강인한 강화학습 알고리즘 설계를 기대할 수 있다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.10
• /
• pp.855-868
• /
• 2004

There are several types of singularities in controlling robotic manipulators: kinematic singularity, algorithmic singularity, semi-kinematic singularity, semi-algorithmic singularity, and representation singularity. The kinematic and algorithmic singularities have been investigated intensively because they are not predictable or difficult to avoid. The problem with these singularities is an unnecessary performance reduction in non-singular region and the difficulty in performance tuning. Tn this paper, we propose a method of avoiding kinematic and algorithmic singularities by applying a task reconstruction approach while maximizing the task performance by calculating singularity measures. The proposed method is implemented by removing the component approaching the singularity calculated by using singularity measure in real time. The outstanding feature of the proposed task reconstruction method (TR-method) is that it is based on a local task reconstruction as opposed to the local joint reconstruction of many other approaches. And, this method has dynamic task priority assignment feature which ensures the system stability under singular regions owing to the change of task priority. The TR-method enables us to increase the task controller gain to improve the task performance whereas this increase can destabilize the system for the conventional algorithms in real experiments. In addition, the physical meaning of tuning parameters is very straightforward. Hence, we can maximize task performance even near the singular region while simultaneously obtaining the singularity-free motion. The advantage of the proposed method is experimentally tested by using the 7-dof spatial manipulator, and the result shows that the new method improves the performance several times over the existing algorithms.