• Journal of the Korean Geosynthetics Society
• /
• v.22 no.2
• /
• pp.47-54
• /
• 2023

In this paper, we propose the technique of optimal search keyword extraction and retrieval for news article classification. The proposed technique was verified as an example of identifying trends related to North Korean construction. A representative Korean media platform, BigKinds, was used to select sample articles and extract keywords. The extracted keywords were vectorized using word embedding and based on this, the similarity between the extracted keywords was examined through cosine similarity. In addition, words with a similarity of 0.5 or higher were clustered based on the top 10 frequencies. Each cluster was formed as 'OR' between keywords inside the cluster and 'AND' between clusters according to the search form of the BigKinds. As a result of the in-depth analysis, it was confirmed that meaningful articles appropriate for the original purpose were extracted. This paper is significant in that it is possible to classify news articles suitable for the user's specific purpose without modifying the existing classification system and search form.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.4
• /
• pp.777-782
• /
• 2012

This paper proposes a technique for improving performance using word senses and user feedback in web information retrieval, compared with the retrieval based on ambiguous user query and index. Disambiguation using query word senses can eliminating the irrelevant pages from the search result. According to semantic categories of nouns which are used as index for retrieval, we build the word sense knowledge-base and categorize the web pages. It can improve the precision of retrieval system with user feedback deciding the query sense and information seeking behavior to pages.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.44-50
• /
• 1995

This paper describes a large-vocabulary continuous speech recognition system using continuous hidden Markov models for the Korean language. To improve the performance of the system, we study on the selection of speech modeling units, inter-word modeling, search algorithm, and grammars. We used triphones as basic speech modeling units, generalized triphones and function word-dependent phones are used to improve the trainability of speech units and to reduce errors in function words. Silence between words is optionally inserted by using a silence model and a null transition. Word pair grammar and bigram model based oil word classes are used. Also we implement a search algorithm to find N-best candidate sentences. A postprocessor reorders the N-best sentences using word triple grammar, selects the most likely sentence as the final recognition result, and finally corrects trivial errors related with postpositions. In recognition tests using a 3,000-word continuous speech database, the system attained $93.1\%$ word recognition accuracy and $73.8\%$ sentence recognition accuracy using word triple grammar in postprocessing.

• Journal of Information Technology Applications and Management
• /
• v.13 no.3
• /
• pp.181-200
• /
• 2006

The purpose of this study is to examine factors influencing online product transformation focusing on benefits of online shopping and word of mouth. Generally, it has been known that buying search goods is more proper than experience goods in the online. However benefits of online shopping and word of mouth make product transformation from experience goods to search goods and the product transformation promote the purchase of experience goods online. We developed a conceptual model of online product transformation including benefits of online shopping(e.g. good price and convenience), online word of mouth (e.g. bulletin board and consumer reviews), and consumer characteristics (e.g. innovativeness and Internet usage). Also, we suggest several research propositions on online product transformation. The implications for marketing strategies of experience goods and furher research direction are suggested.

• Journal of Digital Contents Society
• /
• v.18 no.7
• /
• pp.1419-1425
• /
• 2017

The ultimate goal of legal knowledge search is to obtain optimal legal information based on laws and precedent. Text mining research is actively being undertaken to meet the needs of efficient retrieval from large scale data. A typical method is to use a word embedding algorithm based on Neural Net. This paper demonstrates how to search relevant information, applying Korean law information to word embedding. First, we extracts reference laws from precedents in order and takes reference laws as input of Law2Vec. The model learns a law by predicting its surrounding context law. The algorithm then moves over each law in the corpus and repeats the training step. After the training finished, we could infer the relationship between the laws via the embedding method. The search performance was evaluated based on precision and the recall rate which are computed from how closely the results are associated to the search terms. The test result proved that what this paper proposes is much more useful compared to existing systems utilizing only keyword search when it comes to extracting related laws.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.5
• /
• pp.596-607
• /
• 2017

This study examined the method for adding related to "stomach neoplasms" as filters to the Medical Subject Headings (MeSH) for search as well as a method for improving the search efficiency through a word-proximity search by measuring the distance of co-occurring terms. A total of 8,625 articles published between 2007 and 2016 with the major topic terms "stomach neoplasms" were downloaded from PubMed article titles. The vocabulary to be added to the MeSH for search were analyzed. The search efficiency was verified by 277 articles that had "Stomach Neoplasms" indexed as MEDLINE MeSH in KoreaMed. As a result, 973 terms were selected as the candidate vocabulary. "Gastric Cancer" (2,780 appearances) was the most frequent term and 7,376 compound words (88.51%) combined the histological terms of "stomach" and "neoplasm", such as "gastric adenocarcinoma" and "gastric MALT lymphoma". A total of 5,234 compounds words (70.95%), in which the co-occurring distance was two words, were found. The matching rate through the MEDLINE MeSH and KoreaMed MeSH Indexer was 209 articles (75.5%). The search efficiency improved to 263 articles (94.9%) when the search filters were added, and to 268 articles (96.7%) when the 13 word-proximity search technique of the co-occurring terms was applied. This study showed that the use of a thesaurus as a means of improving the search efficiency in a natural language search could maintain the advantages of controlled vocabulary. The search accuracy can be improved using the word-proximity search instead of a Boolean search.

• Journal of Korea Multimedia Society
• /
• v.19 no.11
• /
• pp.1878-1890
• /
• 2016

Web 2.0 has features produced the content through the user of the participation and share. The content production activities have became active since social network service appear. The social bookmark, one of social network service, is service that lets users to store useful content and share bookmarked contents between personal users. Unlike Internet search engines such as Google and Naver, the content stored on social bookmark is searched based on tag keyword information and unnecessary information can be excluded. Social bookmark can make users access to selected content. However, quick access to content that users want is difficult job because of the user of the participation and share. Our paper suggests a method recommending search word to be able to access quickly to content. A method is suggested by using Collaborative Filtering and Jaccard similarity coefficient. The performance of suggested system is verified with experiments that compare by 'Delicious' and "Feeltering' with our system.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• Journal of Digital Convergence
• /
• v.15 no.12
• /
• pp.333-340
• /
• 2017

Since realtime search words are centered on the fact that the search growth rate of an issue is rapidly increasing in a short period of time, it is not possible to express an issue that maintains interest for a certain period of time. In order to overcome these limitations, this paper evaluates the daily and hourly persistence of the realtime words that belong to the top 10 for a certain period of time and extracts the search word that are constantly interested. Then, we present the method of using the time series analysis and the neural network to know how the interest of the upper search word changes, and show the result of forecasting the near future change through the actual example derived through the method. It can be seen that forecasting through time series analysis by date and artificial neural networks learning by time shows good results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1083-1088
• /
• 2007

In this paper, We investigate the search patterns that are applied to the character based word search and make the search algorithm. We used to various hangout coded set that are KS X 1001 hangeul coded set and unicode 3.0 for the character based word search algorithm. In each case, We study of efficiency of algorithms that are related to hangeul coded set.