• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1649-1659
• /
• 2004

Text Generation is a process of generating comprehensible texts in human languages from some underlying non-linguistic representation of information. Among several sub-processes for text generation to generate coherent texts, this paper concerns referring expression generation which produces different types of expressions to refer to previously-mentioned things in a discourse. Specifically, we focus on pronominalization by zero pronouns which frequently occur in Korean. To build a generation model of referring expressions for Korean, several features are identified based on grammatical information and cost-based centering model, which are applied to various machine learning techniques. We demonstrate that our proposed features are well defined to explain pronominalization, especially pronominalization by zero pronouns in Korean, through 95 texts from three genres - Descriptive texts, News, and Short Aesop's Fables. We also show that our model significantly outperforms previous ones with a 99.9% confidence level by a T-test.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.9
• /
• pp.379-390
• /
• 2019

In this paper, we propose a novel deep neural network model for Vision-and-Language Navigation (VLN) named LVLN (Landmark-based VLN). In addition to both visual features extracted from input images and linguistic features extracted from the natural language instructions, this model makes use of information about places and landmark objects detected from images. The model also applies a context-based attention mechanism in order to associate each entity mentioned in the instruction, the corresponding region of interest (ROI) in the image, and the corresponding place and landmark object detected from the image with each other. Moreover, in order to improve the success rate of arriving the target goal, the model adopts a progress monitor module for checking substantial approach to the target goal. Conducting experiments with the Matterport3D simulator and the Room-to-Room (R2R) benchmark dataset, we demonstrate high performance of the proposed model.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• Proceedings of the KIEE Conference
• /
• 1990.11a
• /
• pp.417-420
• /
• 1990

The conventional quantitative techniques of system analysis are intrinsically unsuited for dealing with humanistic systems. Therefore, the rule based modeling of fuzzy linguistic type has been developed for the analysis of humanistic systems and complex systems and it is very significant for analysis and design of fuzzy logic controller. The activated sludge process is a commonly used method for treating sewage and waste waters. A mathematical tool to build a fuzzy model of the activated sludge process where fuzzy implications and linear reasoning are used is presented in here. A root-mean square error is used as the criterion of the fuzzy model's adequacy to the A.S.P. and the least square method is used for the identification of optimum consequence parameters. A method of modeling of the activated sludge process using its input-output data and simulation results for its application are shown.

• Proceedings of the Korean Institute of Industrial Safety Conference
• /
• 1997.11a
• /
• pp.117-122
• /
• 1997

This paper presents a study on the fuzzy based approach for the safety assessment of human body under ELF electric and magnetic(EM) field considering power system states. The analysis of ELF EM field based on quasi-static method is introduced. UP to the present, the analysis of ELF EM field has been conducted with the consideration of one transmission line, or a power line model only In this paper, however, the power system is included to model the expected and/or unexpected uncertainty caused by the load fluctuation and parameter changes and the states are classified into two types, normal state resulting from normal operation and emergency state from outages. In order to analyze the uncertainty in the normal state, the Monte Carlo Simulation, a statistic approach was introduced and line current and bus voltage distribution are calculated by a contingency analysis method, in the emergency state. To access the safety of human body, the approach based on fuzzy linguistic variable is adopted to overcome the shortcomings of the assessment by a crisp set concept. In order to validate the usefulness of the approach suggested herein, the case study using a sample system with 765(kV) was done. The results are presented and discussed.

• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.1-9
• /
• 2001

In this paper. we present a web-based object model of language resources that are distributed in different places in variable forms. Language resources organized as objects distributed over web sites can be easily utilized to produce application systems of natural language processing. So. it renders effective maintenance of overall language processing environment in that upgrading language resources can lead to the mechanical upgrading of application systems. We implemented a dictionary constructing system for Korean Language (YDK2000). This system can integrate various linguistic dictionaries and also allow to construct high quality application specific dictionaries by connecting them to natural language systems on the Internet.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.2
• /
• pp.96-105
• /
• 1997

In this paper, A new design method of fuzzy modeling is presented for the model identification of nonlinear complex systems. The proposed FPNN(Fuzzy Polynomial Neural Network) modeling implements system structure and parameter identification using GMDH(Group Method of Data Handling) method and linguistic fuzzy implication rules from input and output data of processes. In order to identify premise structure and parameter of fuzzy implication rules, GMDH method and regression polynomial fuzzy reasoning method are used and the least square method is utilized for the identification of optimum consequence parameters. Time series data for gas furnace and those for wastewater treatment process are used for the purpose of evaluating the performance of the proposed FPNN modeling. The results show that the proposed method can produce the fuzzy model with higher accuracy than other works achieved previously.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.4
• /
• pp.194-201
• /
• 2012

Because the difference between products and services are getting less and less, service and manufacturing companies' efforts are increasingly focused on utilizing services to satisfy customers' needs under today's competitive market environment. The value of services depends on service reliability that is identified by satisfaction derived from the relationship between customer needs and service providers. In this paper, we extend concepts from the fault tree analysis for reliability analysis of tangible systems to services. We use an event-based process model to facilitate service design and represent the relationships between functions and failures in a service. The objective of this research is to propose a method for evaluating service reliability based on service processes using service blueprint and FTA. We can identify the failure mode of service in a service delivery process with a service blueprint. The fuzzy membership function is used to characterize the probability of failure based on linguistic terms. FTA is employed to estimate the reliability of service delivery processes with risk factors that are represented as potential failure causes. To demonstrate implementation of the proposed method, we use a case study involving a typical automotive service operation.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.241-254
• /
• 2003

The purpose of the present study was to investigate the sentence comprehension strategies used by Korean/English bilingual children when they listened to sentences of their first language, i.e., Korean. The framework of competition model was employed to analyze the influence of the second language, i.e., English, during comprehension of Korean sentences. The participants included 10 bilingual children (ages 7;4-13;0) and 20 Korean-speaking monolingual children(ages 5;7-6;10) with similar levels of development in Korean language as bilingual children. In an act-out procedure, the children were asked to determine the agent in sentences composed of two nouns and a verb with varying conditions of three cues (case-marker, animacy, and word-order). The results revealed that both groups of children used the case marker cues as the strongest cue among the three. The bilingual children relied on case-marker cues even more than the monolingual children. However, the bilingual children used animacy cues significantly less than the monolingual children. There were no significant differences between the groups in the use of word-order cues. The bilingual children appeared less effective in utilizing animacy cues in Korean sentence comprehension due to the backward transfer from English where the cue strength of animacy is very weak. The influence of the second language on the development of the first language in bilingual children was discussed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4184-4202
• /
• 2021

Text steganography combined with natural language generation has become increasingly popular. The existing methods usually embed secret information in the generated word by controlling the sampling in the process of text generation. A candidate pool will be constructed by greedy strategy, and only the words with high probability will be encoded, which damages the statistical law of the texts and seriously affects the security of steganography. In order to reduce the influence of the candidate pool on the statistical imperceptibility of steganography, we propose a steganography method based on a new sampling strategy. Instead of just consisting of words with high probability, we select words with relatively small difference from the actual sample of the language model to build a candidate pool, thus keeping consistency with the probability distribution of the language model. What's more, we encode the candidate words according to their probability similarity with the target word, which can further maintain the probability distribution. Experimental results show that the proposed method can outperform the state-of-the-art steganographic methods in terms of security performance.