• Journal of Information Processing Systems
• /
• v.8 no.2
• /
• pp.301-314
• /
• 2012

In this paper, two new approaches to align English-Arabic sentences in bilingual parallel corpora based on the Multi-Class Support Vector Machine (MSVM) and the Hidden Markov Model (HMM) classifiers are presented. A feature vector is extracted from the text pair that is under consideration. This vector contains text features such as length, punctuation score, and cognate score values. A set of manually prepared training data was assigned to train the Multi-Class Support Vector Machine and Hidden Markov Model. Another set of data was used for testing. The results of the MSVM and HMM outperform the results of the length based approach. Moreover these new approaches are valid for any language pairs and are quite flexible since the feature vector may contain less, more, or different features, such as a lexical matching feature and Hanzi characters in Japanese-Chinese texts, than the ones used in the current research.

• Communications for Statistical Applications and Methods
• /
• v.22 no.4
• /
• pp.313-320
• /
• 2015

In this research, we compare the efficiency of two test procedures proposed by Prentice and Gloeckler (1978) and Park and Hong (2009) for grouped data with possible right censored observations. Both test statistics were derived using the likelihood ratio principle, but under different semi-parametric models. We review the two statistics with asymptotic normality and consider obtaining empirical powers through a simulation study. The simulation study considers two types of models the location translation model and the scale model. We discuss some interesting features related to the grouped data and obtain null distribution functions with a re-sampling method. Finally we indicate topics for future research.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.341-354
• /
• 2023

The title of a document is the brief summarization of the document. Readers can easily understand a document if we provide them with its title in their preferred styles and the languages. In this research, we propose a cross-lingual and style-based title generation model using multiple adapters. To train the model, we need a parallel corpus in several languages with different styles. It is quite difficult to construct this kind of parallel corpus; however, a monolingual title generation corpus of the same style can be built easily. Therefore, we apply a zero-shot strategy to generate a title in a different language and with a different style for an input document. A baseline model is Transformer consisting of an encoder and a decoder, pre-trained by several languages. The model is then equipped with multiple adapters for translation, languages, and styles. After the model learns a translation task from parallel corpus, it learns a title generation task from monolingual title generation corpus. When training the model with a task, we only activate an adapter that corresponds to the task. When generating a cross-lingual and style-based title, we only activate adapters that correspond to a target language and a target style. An experimental result shows that our proposed model is only as good as a pipeline model that first translates into a target language and then generates a title. There have been significant changes in natural language generation due to the emergence of large-scale language models. However, research to improve the performance of natural language generation using limited resources and limited data needs to continue. In this regard, this study seeks to explore the significance of such research.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.43.1-43.1
• /
• 2019

In this study, we apply a deep learning model to denoising solar magnetograms. For this, we design a model based on conditional generative adversarial network, which is one of the deep learning algorithms, for the image-to-image translation from a single magnetogram to a denoised magnetogram. For the single magnetogram, we use SDO/HMI line-of-sight magnetograms at the center of solar disk. For the denoised magnetogram, we make 21-frame-stacked magnetograms at the center of solar disk considering solar rotation. We train a model using 7004 paris of the single and denoised magnetograms from 2013 January to 2013 October and test the model using 1432 pairs from 2013 November to 2013 December. Our results from this study are as follows. First, our model successfully denoise SDO/HMI magnetograms and the denoised magnetograms from our model are similar to the stacked magnetograms. Second, the average pixel-to-pixel correlation coefficient value between denoised magnetograms from our model and stacked magnetogrmas is larger than 0.93. Third, the average noise level of denoised magnetograms from our model is greatly reduced from 10.29 G to 3.89 G, and it is consistent with or smaller than that of stacked magnetograms 4.11 G. Our results can be applied to many scientific field in which the integration of many frames are used to improve the signal-to-noise ratio.

• The Journal of Korea Robotics Society
• /
• v.4 no.3
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• Proceedings of the Korea Port Economic Association Conference
• /
• 2007.07a
• /
• pp.391-405
• /
• 2007

The purpose of this paper is to verify the two problems(normalization for the different inputs and outputs data, and translation invariant for the negative data) which will be occurred in measuring the seaport DEA(data envelopment analysis) efficiency. The main result is as follow: Normalization and translation invariant in the BCC model for measuring the seaport efficiency by using 26 Korean seaport data in 1995 with two inputs(berthing capacity, cargo handling capacity) and three outputs(import cargo throughput, export cargo throughput, number of ship calls) was verified. The main policy implication of this paper is that the port management authority should collect the more specific data and publish these data on the inputs and outputs in the seaports with consideration of negative(ex. accident numbers in each seaport) and positive value for analyzing the efficiency by the scholars, because normalization and translation invariant in the data was verified.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.382-386
• /
• 2004

Recently, with the machine learning trend, most of the machine translation systems on over the world use two syntax tree sets of two relevant languages to learn syntactic tree transfer rules. However, for the English-Vietnamese language pair, this approach is impossible because until now we have not had a Vietnamese syntactic tree set which is correspondent to English one. Building of a very large correspondent Vietnamese syntactic tree set (thousands of trees) requires so much work and take the investment of specialists in linguistics. To take advantage from our available English-Vietnamese Corpus (EVC) which was tagged in word alignment, we choose the SITG (Stochastic Inversion Transduction Grammar) model to construct English- Vietnamese syntactic tree sets automatically. This model is used to parse two languages at the same time and then carry out the syntactic tree transfer. This English-Vietnamese bilingual syntactic tree set is the basic training data to carry out transferring automatically from English syntactic trees to Vietnamese ones by machine learning models. We tested the syntax analysis by comparing over 10,000 sentences in the amount of 500,000 sentences of our English-Vietnamese bilingual corpus and first stage got encouraging result $(analyzed\;about\;80\%)[5].$ We have made use the TBL algorithm (Transformation Based Learning) to carry out automatic transformations from English syntactic trees to Vietnamese ones based on that parallel syntactic tree transfer set[6].

• Smart Structures and Systems
• /
• v.19 no.6
• /
• pp.679-694
• /
• 2017

The complexity, enlargement and irregularity of structures and multi-directional dynamic loads acting on the structures can lead to unexpected structural behavior, such as torsion. Continuous torsion of the structure causes unexpected changes in the structure's stress distribution, reduces the performance of the structural members, and shortens the structure's lifespan. Therefore, a method of monitoring the torsional behavior is required to ensure structural safety. Structural torsion typically occurs accompanied by displacement, but no model has yet been developed to measure this type of structural response. This research proposes a model for measuring dynamic torsional response of structure accompanied by displacement and for identifying the torsional modal parameter using vision-based displacement measurement equipment, a motion capture system (MCS). In the present model, dynamic torsional responses including pure rotation and translation displacements are measured and used to calculate the torsional angle and displacements. To apply the proposed model, vibration tests for a shear-type structure were performed. The torsional responses were obtained from measured dynamic displacements. The torsional angle and displacements obtained by the proposed model using MCS were compared with the torsional response measured using laser displacement sensors (LDSs), which have been widely used for displacement measurement. In addition, torsional modal parameters were obtained using the dynamic torsional angle and displacements obtained from the tests.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.21 no.6
• /
• pp.527-533
• /
• 2008

This paper proposes a product data model and associated process for CAE activities in context of integrated product development. The data model and process enable Product Lifecycle Management(PLM) systems to integrate currently separated CAE activities into the main product development process. The product view concept in the proposed product data model supports independent CAE activities including analysis of various alternatives based on shared product structures with design departments and seamless translation of the CAE result to design product views. The proposed model is validated through an implementation of a prototype PLM system that can integrate and synchronize CAE process with the company-wide product development process.

• Korean Journal of Computational Design and Engineering
• /
• v.7 no.3
• /
• pp.157-169
• /
• 2002

In the initial stages of ship design, designers represent geometry, arrangement, and dimension of hull structures with 2D geometric primitives such as points, lines, arcs, and drawing symbols. However, these design information(‘2D geometric primitives’) defined in the drawing sheet require more intelligent translation processes by the designers in the next design stages. Thus, the loss of design semantics could be occurred and following design processes could be delayed. In the initial design stages, it is not easy to adopt commercial 3D CAD systems, which have been developed f3r being used in detail and production design stages, because the 3D CAD systems require detailed input for geometry definition. In this study, a semantic product model data structure was proposed, and an initial structural CAD system was developed based on the proposed data structure. Contents(‘product model data and design knowledges’) of the proposed data structure are filled with minimal input of the designers, and then 3D solid model and production material information can be automatically generated as occasion demands. Finally, the applicability of the proposed semantic product model data structure and the developed initial structural CAD system was verified through application to deadweight 300,000ton VLCC(Very Large Crude oil Carrier) product modeling procedure.