• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.9
• /
• pp.4568-4584
• /
• 2016

Steganography based on text generation has become a hot research topic in recent years. However, current text-generation methods which generate texts of normal style have either semantic or syntactic flaws. Note that texts of special genre, such as poem, have much simpler language model, less grammar rules, and lower demand for naturalness. Motivated by this observation, in this paper, we propose a text steganography that utilizes Markov chain model to generate Ci-poetry, a classic Chinese poem style. Since all Ci poems have fixed tone patterns, the generation process is to select proper words based on a chosen tone pattern. Markov chain model can obtain a state transfer matrix which simulates the language model of Ci-poetry by learning from a given corpus. To begin with an initial word, we can hide secret message when we use the state transfer matrix to choose a next word, and iterating until the end of the whole Ci poem. Extensive experiments are conducted and both machine and human evaluation results show that our method can generate Ci-poetry with higher naturalness than former researches and achieve competitive embedding rate.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.627-632
• /
• 2023

대규모 언어 모델은 높은 연산 능력과 방대한 양의 데이터를 기반으로 탁월한 성능을 보이며 자연어처리 분야의 주목을 받고있다. 이러한 모델들은 다양한 언어와 도메인의 텍스트를 처리하는 능력을 갖추게 되었지만, 전체 학습 데이터 중에서 한국어 데이터의 비중은 여전히 미미하다. 결과적으로 이는 대규모 언어 모델이 영어와 같은 주요 언어들에 비해 한국어에 대한 이해와 처리 능력이 상대적으로 부족함을 의미한다. 본 논문은 이러한 문제점을 중심으로, 대규모 언어 모델의 한국어 처리 능력을 향상시키는 방법을 제안한다. 특히, Cross-lingual transfer learning 기법을 활용하여 모델이 다양한 언어에 대한 지식을 한국어로 전이시켜 성능을 향상시키는 방안을 탐구하였다. 이를 통해 모델은 기존의 다양한 언어에 대한 손실을 최소화 하면서도 한국어에 대한 처리 능력을 상당히 향상시켰다. 실험 결과, 해당 기법을 적용한 모델은 기존 모델 대비 nsmc데이터에서 2배 이상의 성능 향상을 보이며, 특히 복잡한 한국어 구조와 문맥 이해에서 큰 발전을 보였다. 이러한 연구는 대규모 언어 모델을 활용한 한국어 적용 향상에 기여할 것으로 기대 된다.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.22-30
• /
• 2019

For effective human-robot interaction, robots need to understand the current situation context well, but also the robots need to transfer its understanding to the human participant in efficient way. The most convenient way to deliver robot's understanding to the human participant is that the robot expresses its understanding using voice and natural language. Recently, the artificial intelligence for video understanding and natural language process has been developed very rapidly especially based on deep learning. Thus, this paper proposes robot vision to audio description method using deep learning. The applied deep learning model is a pipeline of two deep learning models for generating natural language sentence from robot vision and generating voice from the generated natural language sentence. Also, we conduct the real robot experiment to show the effectiveness of our method in human-robot interaction.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.397-402
• /
• 2005

In this paper, to improve the efficiency of welding and user convenience in the shipbuilding industry, a PC-based off-line programming (OLP) technique and the development of a robot transfer unit are presented. The developed OLP system is capable of not only robot motion simulations but also automatic generations of a series of robot programs. The strength of the developed OLP system lies in its flexibility in handling the changes of the welding robot's target objects. Moreover, for a precise transfer of the robot to a desired location, an auxiliary mobile platform named a robot-origin-transfer-unit (ROTU) was developed. To enhance the cornering capability of the platform in a narrow area, the developed ROTU is equipped with 2 steering wheels and 1 driving wheel. Both the OLP and the ROTU were field-tested and their performances were proven successful.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.90-92
• /
• 2002

The SVC(Static Var Compensator) resulted from the FACTS technology can generate or absorb reactive power rapidly so as to increase the transient and voltage stability. In this paper, the SVC is applied to the power system in order to improve the total transfer capability from a viewpoint of static voltage stability and the effects of application of the SVC to the power system are analyzed. The IPLAN, which is a high level language used with PSS/E program, is employed for determining the total transfer capability.

• Proceedings of the KIEE Conference
• /
• 2002.11b
• /
• pp.151-153
• /
• 2002

Using UPFC(Unified Power Flow Controlled), it is possible to control three parameters(voltage, impedance, and phase angle). The UPFC can generate or absorb reactive power rapidly so as to enhance the transient and voltage stability and also influence the power flow. In this paper, the effects of application of the UPFC to the power system are analyzed from a viewpoint of improving the total transfer capability by enhancing voltage stability. The IPLAN, which is a high level language used with PSS/E program, is employed for evaluating the total transfer capability from a f-V curve.

• Phonetics and Speech Sciences
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2018

The current study aimed to investigate the transfer of English word stress rules to the production of Korean trisyllabic words by L1 English learners of Korean. It compared English and Korean speakers' productions of seven Korean words from the corpus L2KSC (Rhee et al., 2005). To this end, it analyzed the syllable duration, intensity, and pitch. The results showed that English and Korean speakers' pronunciations differed markedly in duration and intensity. English learners produced word-initial syllables of greater intensity than Korean speakers, while Korean speakers produced word-final syllables of longer duration than English learners. However, these differences between the two speaker groups were not related to the expected L1 transfer. The tonal patterns produced by English and Korean speakers were similar, reflecting L1 English speakers' learning of the L2 Korean prosodic system.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.1
• /
• pp.32-42
• /
• 2005

In this paper, to improve the efficiency of welding and user convenience in the shipbuilding industry, a PC-based off-line programming (OLP) technique and the development of a robot transfer unit are presented. The developed OLP system is capable of not only robot motion simulations but also automatic generations of a series of robot programs. The strength of the developed OLP system lies in its flexibility in handling the changes of the welding robot's target objects. Moreover, for a precise transfer of the robot to a desired location, an auxiliary mobile platform named a robot-origin-transfer-unit (ROTU) was developed. To enhance the cornering capability of the platform in a narrow area, the developed ROTU is equipped with 2 steering wheels and 1 driving wheel. Both the OLP and the ROTU were field­tested and their performances were proven successful.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.77-89
• /
• 2022

It has been proven through many previous researches that the pretrained language model with a large corpus helps improve performance in various natural language processing tasks. However, there is a limit to building a large-capacity corpus for training in a language environment where resources are scarce. Using the Cross-lingual Post-Training (XPT) method, we analyze the method's efficiency in Korean, which is a low resource language. XPT selectively reuses the English pretrained language model parameters, which is a high resource and uses an adaptation layer to learn the relationship between the two languages. This confirmed that only a small amount of the target language dataset in the relationship extraction shows better performance than the target pretrained language model. In addition, we analyze the characteristics of each model on the Korean language model and the Korean multilingual model disclosed by domestic and foreign researchers and companies.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.3
• /
• pp.64-70
• /
• 2004

Korean and Japanese have same structure of sentences because they belong to same family of languages. So, The transfer driven machine translation is most efficient to translate each other. This paper introduce a method which creates a transfer dictionary for Token Based Transfer Driven Koran-Japanese Machine Translation(TB-TDMT). If the transfer dictionaries are created well, we get rid of useless effort for traditional parsing by performing shallow parsing. The semi-parser makes the dependency tree which has minimum information needed output generating module. We constructed the transfer dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 900 utterances which are collected from travel planning domain. The success-ratio of our system is $92\%$ on restricted testing environment and $81\%$ on unrestricted testing environment.