• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.419-441
• /
• 2008

As the Web and digital libraries have become a commodity, they are used for a variety of purposes and tasks that may require a great deal of cognitive efforts. However, most search engines in the Web and digital libraries support users with only searching and browsing capabilities, leaving all the cognitive burdens of manipulating information objects to the users. We propose a two-level model for human-Web interactions, consisting of knowledge and information spaces, and a tool that provides knowledge space and inter-space operations in addition to searching and browsing at the information level. Knowledge space is an explication of user's conceptual view of the information objects being explored through interactions with the Web or a digital library. Topics are created and related with associations at the knowledge level and connected to information objects in information space. The tool implemented using the Topic Maps framework has been tested for efficacy as an aid to reducing cognitive burden under exploratory search task.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.141-150
• /
• 2021

Based on Artificial Intelligence technology, AI-enabled warfare is expected to become the main issue in the future warfare. Natural language processing technology is a core technology of AI technology, and it can significantly contribute to reducing the information burden of underrstanidng reports, information objects and intelligences written in natural language by commanders and staff. In this paper, we propose a Language model-based Multi-source Information Integration (LAMII) framework to reduce the information overload of commanders and support rapid decision-making. The proposed LAMII framework consists of the key steps of representation learning based on language models in self-supervsied way and document integration using autoencoders. In the first step, representation learning that can identify the similar relationship between two heterogeneous sentences is performed using the self-supervised learning technique. In the second step, using the learned model, documents that implies similar contents or topics from multiple sources are found and integrated. At this time, the autoencoder is used to measure the information redundancy of the sentences in order to remove the duplicate sentences. In order to prove the superiority of this paper, we conducted comparison experiments using the language models and the benchmark sets used to evaluate their performance. As a result of the experiment, it was demonstrated that the proposed LAMII framework can effectively predict the similar relationship between heterogeneous sentence compared to other language models.