• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.322-327
• /
• 2017

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long-Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment's result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.6
• /
• pp.1495-1507
• /
• 1997

Among a number of approaches to text compression, adaptive dictionary schemes based on a sliding window have been very frequently used due to their high performance. The LZ77 algorithm is the most efficient algorithm which implements such adaptive schemes for the practical use of text compression. This paperpresents a VLSI architecture designed for processing the LZ77 algorithm in parallel. Compared with the other VLSI architectures developed so far, the proposed architecture provides the more viable solution to high performance with regard to its throughput, efficient implementation of the VLSI systolic arrays, and hardware scalability. Indeed, without being affected by the size of the sliding window, our system has the complexity of O(N) for both the compression and decompression and also requires small wafer area, where N is the size of the input text.

• Journal of KIISE:Software and Applications
• /
• v.32 no.2
• /
• pp.85-98
• /
• 2005

Recently, a lot of researches about mobile vision using Personal Digital Assistant(PDA) has been attempted. Many CPUs for PDA are integer CPUs, which have no floating-computation component. It results in slow computation of the algorithms peformed by vision system or image processing, which have much floating-computation. In this paper, in order to resolve this weakness, we propose the Client(PDA)/server(PC) architecture which is connected to each other with a wireless LAN, and we construct the system with pipelining processing using two CPUs of the Client(PDA) and the Server(PC) in image sequence. The Client(PDA) extracts tentative text regions using Edge Density(ED). The Server(PC) uses both the Multi-1.aver Perceptron(MLP)-based texture classifier and Connected Component(CC)-based filtering for a definite text extraction based on the Client(PDA)'s tentativel99-y extracted results. The proposed method leads to not only efficient text extraction by using both the MLP and the CC, but also fast running time using Client(PDA)/server(PC) architecture with the pipelining processing.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.646-654
• /
• 2007

In recent years, the use of text inserted into TV contents has grown to provide viewers with better visual understanding. In this paper, video text is defined as superimposed text region located of the bottom of video. Video text extraction is the first step for video information retrieval and video indexing. Most of video text detection and extraction methods in the previous work are based on text color, contrast between text and background, edge, character filter, and so on. However, the video text extraction has big problems due to low resolution of video and complex background. To solve these problems, we propose a method to extract text from videos using the Harris corner detector. The proposed algorithm consists of four steps: corer map generation using the Harris corner detector, extraction of text candidates considering density of comers, text region determination using labeling, and post-processing. The proposed algorithm is language independent and can be applied to texts with various colors. Text region update between frames is also exploited to reduce the processing time. Experiments are performed on diverse videos to confirm the efficiency of the proposed method.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.237-245
• /
• 2001

Automated essay grading has been proposed for over thirty years. Only recently have practical implementations been constructed and tested. This paper investigated the role of the nearest-neighbour algorithm within the information retrieval as a way of grading the essay automatically called Automated Essay Grading System. It intended to offer teachers an individualized assistance in grading the student\`s essay. The system involved several processes, which are the indexing, the structuring of the model answer and the grade processing. The indexing process comprised the document indexing and query processing which are mainly used for representing the documents and the query. Structuring the model answer is actually preparing the marking scheme and the grade processing is the process of assessing the essay. To test the effectiveness of the developed algorithms, the algorithms are tested against the History text in Malay. The result showed that th information retrieval and the nearest-neighbour algorithm are practical combination that offer acceptable performance for grading the essay.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.100-106
• /
• 2021

Over the past few decades, natural language processing research has not made much. However, the widespread use of deep learning and neural networks attracted attention for the application of neural networks in natural language processing. Sentiment analysis is one of the challenges of natural language processing. Emotions are things that a person thinks and feels. Therefore, sentiment analysis should be able to analyze the person's attitude, opinions, and inclinations in text or actual text. In the case of emotion analysis, it is a priority to simply classify two emotions: positive and negative. In this paper we propose the deep learning based sentimental analysis system according to various optimizer that is SGD, ADAM and RMSProp. Through experimental result RMSprop optimizer shows the best performance compared to others on IMDB data set. Future work is to find more best hyper parameter for sentimental analysis system.

• Genomics & Informatics
• /
• v.18 no.2
• /
• pp.13.1-13.6
• /
• 2020

The prototype version of the full-text corpus of Genomics & Informatics has recently been archived in a GitHub repository. The full-text publications of volumes 10 through 17 are also directly downloadable from PubMed Central (PMC) as XML files. During the Biomedical Linked Annotation Hackathon 6 (BLAH6), we experimented with converting, annotating, and updating 301 PMC full-text articles of Genomics & Informatics using PubAnnotation, a system that provides a convenient way to add PMC publications based on PMCID. Thus, this review aims to provide a tutorial overview of practicing the iterative task of named entity recognition with the PubAnnotation/PubDictionaries/TextAE ecosystem. We also describe developing a conversion tool between the Genia tagger output and the JSON format of PubAnnotation during the hackathon.

• International Journal of Contents
• /
• v.10 no.3
• /
• pp.35-40
• /
• 2014

Text line segmentation is a critical task in handwritten document recognition. In this paper, we propose a novel text-line-segmentation method using baseline estimation and watershed. The baseline-detection algorithm estimates the baseline using Adaptive Head-Tail Connection (AHTC) on the document. Then, the watershed method segments the line region using the baseline-detection result. Finally, the text lines are separated by watershed result and a post-processing algorithm defines the lines more correctly. The scheme successfully segments text lines with 97% accuracy from the handwritten document images in the ICDAR database.

• Genomics & Informatics
• /
• v.16 no.3
• /
• pp.75-77
• /
• 2018

Genomics & Informatics (NLM title abbreviation: Genomics Inform) is the official journal of the Korea Genome Organization. Text corpus for this journal annotated with various levels of linguistic information would be a valuable resource as the process of information extraction requires syntactic, semantic, and higher levels of natural language processing. In this study, we publish our new corpus called GNI Corpus version 1.0, extracted and annotated from full texts of Genomics & Informatics, with NLTK (Natural Language ToolKit)-based text mining script. The preliminary version of the corpus could be used as a training and testing set of a system that serves a variety of functions for future biomedical text mining.