• Language and Information
• /
• v.13 no.1
• /
• pp.1-20
• /
• 2009

Summarization is a complex cognitive task and its simulation is very difficult for machines. This paper presents an automatic summarization strategy that is based on a discourse categorization of the textual information. This categorization is carried out by the automatic identification of discourse markers in texts. We defend here the use of discourse methods in automatic summarization. Two evaluations of the summarization strategy are presented. The summaries produced by our strategy are evaluated with summaries produced by humans and other applications. These two evaluations display well the capacity of our application, based on EXCOM, to produce summaries comparable to the summaries of other applications.

• Journal of The Korean Association of Information Education
• /
• v.3 no.1
• /
• pp.33-43
• /
• 1999

Most educational Web contents developed so far can be regarded' as another type of printed textbooks since they are made up of static lists of textual information. It results in a lack of capability in such educational viewpoints as interaction between students and/or teachers, self-directed learning of individual students, and so on. This paper proposes a new style of Web contents, which can improve the self-directed learning capabilities as well as the interaction between students, with the topic of "the life cycle of frog" that the student studies in the third year of elementary school. It has been designed to provide BBS and a studying material appropriate to the achievement level of individual students, and implemented with DHTML and Java.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.2
• /
• pp.165-182
• /
• 2001

In this paper, we describe a design and implementation of the Wireless Markup Language(WML) compiler to deploy wireless Internet services effectively. The WML compiler translates textual WML decks into binary ones in order to reduce the traffic on wireless links that have relatively low bandwidth to wireline links and mitigate the processing overhead of WML decks on, wireless terminals that have relatively low processing power to fixed workstations. In addition, it takes over the overhead of eXtensible Markup Language(XML) well-formedness and validation processes. The WML compiler consists of the lexical analyzer and parser modules. The granunar for the WML parser module is LALR(1) context-free grammar that is designed based on XML 1.0 and WML 1.2 DTD(Document Type Definition) with the consideration of the Wireless Application Protocol Binary XML grammar. The grammar description is converted into a C program to parse that grammar by using parser generator. Even though the tags in WML will be extended or WML DTD will be upgraded, this approach has the advantage of flexibility because the program is generated by modifying just the changed parts. We have verified the functionality of the WML compiler by using a WML decompiler in the public domain and by using the Nokia WAP Toolkit as a WAP client. To measurethe compressibility gain of the WML compiler, we have tested a large number of textual WML decks and obtained a maximum 85 %. As the effect of compression is reduced when the portion of general textual strings increases relative to one of the tags and attributes in a WML deck, an extended encoding method might be needed for specific applications such as compiling of the WML decks to which the Hyper Text Markup Language document is translated dynamically.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2687-2692
• /
• 2003

Recent advancement in information technology requires new interpretations for the space among human, machines and environment. Investigation of space between information and human could lead to the proper ways, in which human and machines meet. Various concepts regarding space have been explored in terms of “virtual reality in cyberspace” and “embodiment in tangible space.” “Mom (embodiment),” space, virtuality, sensation/perception, and interactive technology are some of the key ideas to be explored. Human “Mom” is such a fundamental membrane through which human can interact with the environment physically and mentally. An embodied interaction paradigm, based on “Mom,” is investigated. This leads to interactive technology paradigm. Sound space is an invisible but a tangible space in a sense that it travels in emotional tremors and stimulates new sensations and perceptions. Three cases are introduced to experiment such tangible space as a new and proper interactive paradigm. Also, a historical model of interaction is reviewed, which includes electrical, symbolic, textual, graphical, tangible, and social interaction.

• International Journal of Contents
• /
• v.14 no.1
• /
• pp.1-6
• /
• 2018

Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.

• Journal of Korea Multimedia Society
• /
• v.6 no.4
• /
• pp.565-575
• /
• 2003

This paper proposed context based annotation model and annotation ambiguity correction methods. The proposed model provides various annotation types, semantic models, and pen-based free drawing interface. Annotation correction method that is specifically based on the context which includes various textual and structure information between free-form marking and annotation. Also, interface for XML environment using the proposed model and correction methods is proposed and possibilities of application is looked at. The results from the implementation of the proposed method show that the annotated areas included in the free-form marking information are more accurate, achieving more accurate exchange results amongst multiple users in a heterogeneous document environment

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.99-100
• /
• 2018

Citation of academic research papers is a very important result for academic researchers, and their utilization is becoming an important evaluation factor. Most papers are composed of authors' keywords. However, there may be some papers with little relevance between the textual content and the presented keywords. Therefore, it is necessary to extract and present important keywords through objective methods for titles and abstracts of theses. In this paper, we present the development results of important keywords through data visualization for academic research papers.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.1
• /
• pp.221-229
• /
• 2012

A model for expressing meta data syntax in the eXtensible Markup Language(XML) was developed to increase the portability of the Arden Syntax in medical treatment. In this model that is Arden syntax uses two syntax checking mechanisms, first an XML validation process, and second, a syntax check using an XSL style sheet. Two hundred seventy-seven examples of MLMs were transformed into MLMs in ArdenML and validated against the schema and style sheet. Both the original MLMs and reverse-parsed MLMs in ArdenML were checked using a Arden Syntax checker. The textual versions of MLMs were successfully transformed into XML documents using the model, and the reverse-parse yielded the original text version of MLMs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.3
• /
• pp.150-170
• /
• 2008

In recent years, main focus of research on image retrieval techniques is on content-based image retrieval. Text-based image retrieval schemes, on the other hand, provide semantic support and efficient retrieval of matching images. In this paper, based on Formal Concept Analysis (FCA), we propose a new image indexing and retrieval technique. The proposed scheme uses keywords and textual annotations and provides semantic support with fast retrieval of images. Retrieval efficiency in this scheme is independent of the number of images in the database and depends only on the number of attributes. This scheme provides dynamic support for addition of new images in the database and can be adopted to find images with any number of matching attributes.