• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.3
• /
• pp.424-431
• /
• 2012

In information retrieval, search engine provide the rank of web page and the summary of the web page information to user. Snippet is a summaries information of representing web pages. Visiting the web page by the user is affected by the snippet. User sometime visits the wrong page with respect to user intention when uses snippet. The snippet extraction method is difficult to accurate comprehending user intention. In order to solve above problem, this paper proposes a new snippet extraction method using fuzzy implication operator and relevance feedback. The proposed method uses relevance feedback to expand the use's query. The method uses the fuzzy implication operator between the expanded query and the web pages to extract snippet to be well reflected semantic user's intention. The experimental results demonstrate that the proposed method can achieve better snippet extraction performance than the other methods.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.7
• /
• pp.1832-1840
• /
• 1999

Since the existed Korean Web IR systems generally use boolean system, it is difficult to retrieve the information to be wanted at one time. Also, because of the feature that web documents have the frequent abbreviation and many links, the keyword extraction using the inverted document frequency extracts the improper keywords for adding ambiguous meaning problem. Therefore, users must repeat the modification of the queries until they get the proper information. In this paper, we design and implement the relevance feedback agent system for resolving the above problems. The relevance feedback agent system extracts the proper information in response to user's preferred keywords and stores these keywords in preference DB table. When users retrieve this information later, the relevance feedback agent system will search it adding relevant keywords to user's queries. As a result of this method, the system can reduce the number of modification of user's queries and improve the efficiency of the IR system.

• Journal of Intelligence and Information Systems
• /
• v.13 no.1
• /
• pp.1-14
• /
• 2007

Character images for the background screen of cell phones are one of the fast growing sectors of the mobile content market. However, character image buyers currently experience tremendous difficulties in searching for desired images due to the awkward image search process. Content-based image retrieval (CBIR) widely used for image retrieval could be a good candidate as a solution to this problem, but it needs to overcome the limitation of the mobile Internet environment where an initial query set (IQS) cannot be easily provided as in the PC-based environment. We propose a new approach, IQS-AutoGen, which automatically generates an initial query set for CBIR on the mobile Internet. The approach applies the collaborative filtering (CF), a well-known recommendation technique, to the CBIR process by using users' preference information collected during the relevance feedback process of CBIR. The results of the experiment using a PC-based prototype system show that the proposed approach successfully satisfies the initial query requirement of CBIR in the mobile Internet environment, thereby outperforming the current image search process on the mobile Internet.

• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.43-66
• /
• 2008

Currently be proceeded a lot of researchers for 'user information demand description' for interface of an information retrieval system or Web search engines, but user information demand description for a natural language form is a difficult situation. These reasons are as they cannot provide the semantic similarity that an information retrieval model can be completely satisfied with variety regarding an information demand expression and semantic relevance for user information description. Therefore, this study using the description logic that is a knowledge representation base of OWL and a vector model-based weight between concept, and to be able to satisfy variety regarding an information demand expression and semantic relevance proposes a decision way for perfect assistances of user information demand description. The experiment results by proposed method, semantic similarity of a polyseme and a synonym showed with excellent performance in decision.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.383-392
• /
• 2006

In this paper, we propose a new relevance feedback algorithm using Probabilistic Neural Networks(PNN) while supporting multi-class learning. Then, to validate the effectiveness of our feedback approach, we incorporate the proposed algorithm into our region-based image retrieval tool, FRIP(Finding Regions In the Pictures). In our feedback approach, there is no need to assume that feature vectors are independent, and as well as it allows the system to insert additional classes for detail classification. In addition, it does not have a long computation time for training because it only has four layers. In the PNN classification process, we store the user's entire past feedback actions as a history in order to improve performance for future iterations. By using a history, our approach can capture the user's subjective intension more precisely and prevent retrieval performance errors which originate from fluctuating or degrading in the next iteration. The efficacy of our method is validated using a set of 3000 images derived from a Corel-photo CD.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.5
• /
• pp.221-226
• /
• 2024

In information retrieval, queries come in various types, ranging from abstract queries to those containing specific keywords, making it a challenging task to accurately produce results according to user demands. Additionally, search systems must handle queries encompassing various elements such as typos, multilingualism, and codes. Reranking is performed through training suitable documents for queries using DeBERTa, a deep learning model that has shown high performance in recent research. To evaluate the effectiveness of the proposed method, experiments were conducted using the test collection of the Product Search Track at the TREC 2023 international information retrieval evaluation competition. In the comparison of NDCG performance measurements regarding the experimental results, the proposed method showed a 10.48% improvement over BM25, a basic information retrieval model, in terms of search through query error handling, provisional relevance feedback-based product title-based query expansion, and reranking according to query types, achieving a score of 0.7810.

• The Korean Journal of Archival Studies
• /
• no.19
• /
• pp.57-102
• /
• 2009

Recently, distribution of record via web and coefficient of utilization are increase. so, Archival information service using website becomes essential part of record center. The main point of archival information service by website is making record information retrieval easy. It has need of matching user's request and representation of record resources correctly to making archival information retrieval easy. Archivist and record manager have used various information representation tools from taxonomy to recent thesaurus, still, the accuracy of information retrieval has not solved. This study constructed record retrieval system based on Topic Map by modeling record resources which focusing on description metadata of the records to improve this problem. The target user of the system is general web users and its range is limited to the president related sources in the National Archives Portal Service. The procedure is as follows; 1) Design an ontology model for archival information service based on topic map which focusing on description metadata of the records. 2) Buildpractical record retrieval system with topic map that received information source list, which extracted from the National Archives Portal Service, by editor. 3) Check and assess features of record retrieval system based on topic map through user interface. Through the practice, relevance navigation to other record sources by semantic inference of description metadata is confirmed. And also, records could be built up as knowledge with result of scattered archival sources.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1302-1306
• /
• 2004

This paper proposes a model for information filtering (IF) on the Web. The user information need is described into two levels in this model: profiles on category level, and Boolean queries on document level. To efficiently estimate the relevance between the user information need and documents by fuzzy, the user information need is treated as a rough set on the space of documents. The rough set decision theory is used to classify the new documents according to the user information need. In return for this, the new documents are divided into three parts: positive region, boundary region, and negative region. We modified user profile by the user's relevance feedback and discerning words in the documents. In experimental we compared the results of three methods, firstly is to search documents that are not passed the filtering system. Second, search documents that passed the filtering system. Lastly, search documents after modified user profile. The result from using these techniques can obtain higher precision.

• Journal of the Korean Society for information Management
• /
• v.30 no.2
• /
• pp.297-315
• /
• 2013

This study aims to analyze and evaluate term suggestion services of major search portals, Naver and Google Korea. In particular, this study evaluated relevance and currency of related search terms provided, and analyzed characteristics such as number and distribution of terms, and queries that did not produce terms. This study also analyzed types of terms in terms of the relationship between queries and terms, and investigated types and characteristics of harmful terms and terms with grammatical errors. Finally, Korean queries and English queries, and popular queries and academic queries were compared in terms of the amount and relevance of search terms provided. The results of this study show that the relevance and currency of Naver's related search terms are somewhat higher than those of Google. Both Naver and Google tend to add terms to or delete terms from original queries, and provide identical search terms or synonym terms rather than providing entirely new search terms. The results of this study can be implemented to the portal's effective development of term suggestion services.

• Journal of the Korean Society for information Management
• /
• v.31 no.3
• /
• pp.181-200
• /
• 2014

This study aims to analyze and evaluate video search services of major search portals, Naver and Google Korea. In particular, this study analyzed characteristics such as collection distribution, yearly distribution, the ratio of redundant search results, the ratio of advertising, and the quality of videos. This study also evaluated relevance, credibility, and currency of video search results, and investigated the factors that influence relevance and credibility. Finally, types and characteristics of error results were analyzed. The results of this study show that the relevance of Google's video search results is higher than those of Naver, whereas currency of Naver's search results is somewhat higher than those of Google. Google has more high resolution videos than Naver, and Naver has more advertising than Google. Both Google and Naver return many redundant videos in the search results. The results of this study can be implemented to the portal's effective development of video search services.