• 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.

• Journal of Information Technology Applications and Management
• /
• v.27 no.1
• /
• pp.49-58
• /
• 2020

Lately, a large amount of textual data have been poured out of the Internet and the technology to refine them is needed. Most of these data are long text and often have no title. Therefore, in this paper, we propose a technique to combine the sequence-to-sequence model of RNN and the REINFORCE algorithm to generate the title of the long text automatically. In addition, the TextRank algorithm was applied to extract a summarized text to minimize information loss in order to protect the shortcomings of the sequence-to-sequence model in which an information is lost when long texts are used. Through the experiment, the techniques proposed in this study are shown to be superior to the existing ones.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.11
• /
• pp.2679-2689
• /
• 1997

In this paper, a multimedia authoring system using temporal/spatial synchronization manager is designed and implemented to support easy and efficient generation of multimedia title. For this goal, a flowchart-oriented logic generator which represents a title author's design intent into a practical title composition logic without extra translation process, and a logic interpreter which translate and implement the generated title logic, are designed. Furthermore, a temporal/spatial synchronization manager which manages temporal/spatial synchronization information between media data for multimedia representation, is designed. Especially, a temporal specification model and MRL, a formal language for the model, are designed to synchronize the temporal relation between media objects. The MRL represents a complex temporal relation by simple and clear form, and synchronizes efficiently multimedia representation according to the author's intent. A presentation frame editor which makes coincidence between visible size of representation media and attachment point, is implemented for spatial synchronization.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.175-184
• /
• 2022

Travel YouTubers who cross the boundary between tradition and novelty communicate by sharing their activities with others through SNS-based media. Media content should not only satisfy individuals, nor should it be too purpose-oriented. YouTube channels should be operated so that users can easily access content naturally, and more diverse methods can be pursued based on usage patterns and satisfaction theory. This study is about the type of perception of Generation Z on travel YouTube titles. As a result of conducting QUANL program analysis on 34 Q samples and 28 P samples from the Q methodological perspective, a total of three types were found. For types with unique characteristics, the first type was named "attention of keywords that draw imagination," the second type was "preferred to stories that stimulate curiosity," and the third type was "image satisfaction reflecting expectations." In addition, considering the characteristics of each type found, the scalability and strategic plan of the activities that Generation Z travel YouTubers want to unfold were presented.

• Journal of the Korean Society for information Management
• /
• v.40 no.2
• /
• pp.183-209
• /
• 2023

The purpose of this study is to evaluate the Dublin Core metadata generated by ChatGPT using book covers, title pages, and colophons from a collection of books. To achieve this, we collected book covers, title pages, and colophons from 90 books and inputted them into ChatGPT to generate Dublin Core metadata. The performance was evaluated in terms of completeness and accuracy. The overall results showed a satisfactory level of completeness at 0.87 and accuracy at 0.71. Among the individual elements, Title, Creator, Publisher, Date, Identifier, Rights, and Language exhibited higher performance. Subject and Description elements showed relatively lower performance in terms of completeness and accuracy, but it confirmed the generation capability known as the inherent strength of ChatGPT. On the other hand, books in the sections of social sciences and technology of DDC showed slightly lower accuracy in the Contributor element. This was attributed to ChatGPT's attribution extraction errors, omissions in the original bibliographic description contents for metadata, and the language composition of the training data used by ChatGPT.

• Korean Educational Research Journal
• /
• v.38 no.3
• /
• pp.189-210
• /
• 2018

This paper begins with the notion of 'pick-me generation', which refers to today's young generation in Korea. It is named after the title of a song introduced at the Television programme for the competitive audition for girl-group singers. This name gives an idea of the atmosphere of the competition that the current young generation experiences in South Korea. In parallel to it, the research examines the meaning of freedom and choice in democratic education in Oh Chunsuck, in his later work in particular. This paper attempts to demonstrate the possibility to relate Oh's notion of freedom and democracy in relation to Han who critically analyses contemporary discourses on neo-liberalism and democracy. This paper re-views Oh's ideals of democracy and education within its own limitations on freedom. The argument extends Oh's idea of freedom and ethical democracy to the idea of freedom that is relevant to today's younger generation.

• Journal of Advanced Navigation Technology
• /
• v.16 no.1
• /
• pp.54-61
• /
• 2012

The WAVE specification, which for the Next-Generation ITS environment is a common title: IEEE 802.11p and IEEE P1609 specifications. These days, there are many activities for researching WAVE specification by release of the IEEE 802.11p specification. The difference between high-speed vehicle environment and the indoor environment, the wireless communication channel mode is that much more severe. Thus, the wireless communication system design, temperature, noise, multipath fading and can degrade the performance of the system points should be fully considered matters of. In this paper, we showed WAVE wireless communication system which based on IEEE 802.11p PHY/MAC design process, and also showed solving process many implementation problems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1210-1216
• /
• 2003

Traditional indexing mechanism are based on the song's metadata such as the title and the composer and so on. However, these system have a major limitation that users have to know the metadata of the songs they want to retrieve. In order to solve these limitation, we proposed a rhythm extraction system that allows users to retrieve music information efficiently from a large music database using the rhythm that is defined as the parts of the music.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.4
• /
• pp.251-258
• /
• 2005

Automatic document classification may differ significantly according to the characteristics of documents that are subject to classification, as well as classifier's performance. This research identifies e-mail document's characteristics to apply a three-step preprocessing algorithm that can minimize e-mail document's atypical characteristics. In the first 5go, uncertain based sampling algorithm that used Mean Absolute Deviation(MAD), is used to address the question of selection learning document for the rule generation at the time of classification. In the subsequent stage, Weighted vlaue assigning method by attribute is applied to increase the discriminating capability of the terms that appear on the title on the e-mail document characteristic level. in the third and last stage, accuracy level during classification by each category is increased by using Naive Bayesian Presumptive Algorithm's Dynamic Threshold. And, we implemented an E-Mail Recommendtion System using a three-step preprocessing algorithm the enable users for direct and optimal classification with the recommendation of the applicable category when a mail arrives.