• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.1
• /
• pp.18-33
• /
• 2014

A Word is the smallest unit for text analysis, and the premise behind most text-mining algorithms is that the words in given documents can be perfectly recognized. However, the newly coined words, spelling and spacing errors, and domain adaptation problems make it difficult to recognize words correctly. To make matters worse, obtaining a sufficient amount of training data that can be used in any situation is not only unrealistic but also inefficient. Therefore, an automatical word extraction method which does not require a training process is desperately needed. WordRank, the most widely used unsupervised word extraction algorithm for Chinese and Japanese, shows a poor word extraction performance in Korean due to different language structures. In this paper, we first discuss why WordRank has a poor performance in Korean, and propose a customized WordRank algorithm for Korean, named KR-WordRank, by considering its linguistic characteristics and by improving the robustness to noise in text documents. Experiment results show that the performance of KR-WordRank is significantly better than that of the original WordRank in Korean. In addition, it is found that not only can our proposed algorithm extract proper words but also identify candidate keywords for an effective document summarization.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.509-517
• /
• 2023

The reactive web service provides a related word recommendation system using the TextRank algorithm and a word-based idea generation service selected by the user. In the related word recommendation system, the method of weighting each word using the TextRank algorithm and the probability output method using SoftMax are discussed. The idea generation service discusses the idea generation method and the artificial intelligence reinforce-learning method using mini-GPT. The reactive web discusses the linkage process between React, Spring Boot, and Flask, and describes the overall operation method. When the user enters the desired topic, it provides the associated word. The user constructs a mind map by selecting a related word or adding a desired word. When a user selects a word to combine from a constructed mind-map, it provides newly generated ideas and related patents. This web service can share generated ideas with other users, and improves artificial intelligence by receiving user feedback as a horoscope.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.1
• /
• pp.110-114
• /
• 2010

We describe a new method for text categorization using TextRank algorithm. Text categorization is a problem that over one pre-defined categories are assigned to a text document. TextRank algorithm is a graph-based ranking algorithm. If we consider that each word is a vertex, and co-occurrence of two adjacent words is a edge, we can get a graph from a document. After that, we find important words using TextRank algorithm from the graph and make feature which are pairs of words which are each important word and a word adjacent to the important word. We use classifiers: SVM, Na$\ddot{i}$ve Bayesian classifier, Maximum Entropy Model, and k-NN classifier. We use non-cross-posted version of 20 Newsgroups data set. In consequence, we had an improved performance in whole classifiers, and the result tells that is a possibility of TextRank algorithm in text categorization.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.157-163
• /
• 2018

People who use SNS publish their diverse ideas on SNS every day. The data posted on the SNS contains many people's thoughts and opinions. In particular, popular keywords served on Twitter compile the number of frequently appearing words in user posts and rank them. However, this method is sensitive to unnecessary data simply by listing duplicate words. The proposed method determines the ranking based on the topic of the word using the relationship diagram between words, so that the influence of unnecessary data is less and the main word can be stably extracted. For the performance comparison in terms of the descending keyword rank and the ratios of meaningless keywords among high rank 20 keywords, we make a comparison between the proposed scheme which is based on morphological analysis and PageRank, and the existing scheme which is based on the number of appearances. As a result, the proposed scheme and the existing scheme have included 55% and 70% of meaningless keywords among high rank 20 keywords, respectively, where the proposed scheme is improved about 15% compared with the existing scheme.

• Journal of Korean Academy of Nursing
• /
• v.13 no.3
• /
• pp.106-118
• /
• 1983

The main purpose of this study is to systematically classify words indicating pain in terms of their ranks in each subclass. This study is a part of developing a Korean Pain Measurement Tool. This study didnot include exploration of each word's dimension such as sensory or affective. Eighty three Korean words tentatively classified in 19 subclasses in previous study were used for this study. At least three to six words were included in each subclass and the words were randomly placed in which each subject indicates their rank of pain degree. One hundred and fifty nursing students and one hundred clinical nurses were requested to indicate the rank of each word. One hundred and sixteen students and eighty three nurses completed the ratings for analysis. The data were collected from June 1983 to July 1983. The data using ordinal scale were analyzed by Friedman ANOVA to test significant difference between rank means. All of pain words indicated significant rank mean difference in all of 19 subclasses. Some of the words were either cancelled or replaced by other words, or rearranged for their ranks. Subclasses of which words were cancelled were 1) Simple stimulating pain, 2) Punctuate pressure, 3) peripheral nerve pain, 4) radiation pain, 5) punishment-related pain, and 6) suffering-related pain. Subclasses of which words were replaced or rearranged were 1) incisive pressure, 2) constrictive pressure, 3) dull pain, 4) tract pain, 5) digestion-related pain and 6) fear-related pain. Four subclasses such as traction pressure, thermal, cavity pressure, and fatigue- elated pain indicated significant differences among rank means in each subclasses and showed no visible overlaps of the ranks among means. Further research is needed using high level measurement of pain degree of each word and more sophisticated analysis of the pain degrees. Three pain words which would be related to chemical stimulation were newly explored and included as a new subclass. Through this study, the total number of subclasses increases from 19 to 20 and the total number of Korean words in the scale decreases from 83 to 80.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.124-129
• /
• 2006

This parer presents a method of ranking translation word selection for Korean verbs based on lexical knowledge contained in a bilingual Korean-English dictionary and WordNet that are easily obtainable knowledge resources. We focus on deciding which translation of the target word is the most appropriate using the measure of semantic relatedness through the 45 extended relations between possible translations of target word and some indicative clue words that play a role of predicate-arguments in source language text. In order to reduce the weight of application of possibly unwanted senses, we rank the possible word senses for each translation word by measuring semantic similarity between the translation word and its near synonyms. We report an average accuracy of $51\%$ with ten Korean ambiguous verbs. The evaluation suggests that our approach outperforms the default baseline performance and previous works.

• Journal of KIISE
• /
• v.44 no.5
• /
• pp.522-536
• /
• 2017

Keyword extraction can be utilized in text mining of massive documents for efficient extraction of subject or related words from the document. In this study, we proposed a hierarchical graph model based on the co-occurrence relationship, the intrinsic dependency relationship between words, and common sub-word in a single document. In addition, the enhanced TextRank algorithm that can reflect the influences of outgoing edges as well as those of incoming edges is proposed. Subsequently a novel keyword extraction scheme using the proposed hierarchical graph model and the enhanced TextRank algorithm is proposed to extract representative keywords from a single document. In the experiments, various evaluation methods were applied to the various subject documents in order to verify the accuracy and adaptability of the proposed scheme. As the results, the proposed scheme showed better performance than the previous schemes.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.231-240
• /
• 2011

Many search algorithms have been implemented by many researchers on the world wide web. One of the best algorithms is Google using PageRank technology. PageRank approach computes the number of inlink of each documents then ranks documents in the order of inlink members. But it is difficult to find the results that user needs, because this method find documents not valueable for a person but valueable for the public. To solve this problem, We use the WordNet for analysis of the user's query history. This paper proposes a personalized search engine using the user's query history and PageRank Check. We compared the performance of the proposed approaches with google search results in the top 30. As a result, the average of the r-precision for the proposed approaches is about 60% and it is better as about 14%.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1009-1014
• /
• 1994

This paper improves the previously proposed spectral mapping method for supervised speaker adaptation in which a mapped spectrum is interpolated from speaker difference vectors at typical spectra based on a minimized distortion criterion. In estimating these difference vectors, it is important to find an appropriate number of typical points. The previous method empirically adjusts the number of typical points, while the present method optimizes the effective number by rank reduction of normal equation. This algorithm was applied to a supervised speaker adaptation for Korean word recognition using the templates form a prototype male speaker. The result showed that the rank reduction technique not only can automatically determine an optimal number of code vectors, but also slightly improves the recognition scores compared with those obtained by the previous method.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.62-66
• /
• 2016

문서의 의미 기반 처리를 위해서 문서의 내용을 대표하는 키워드를 추출하는 것은 정확성과 효율성 측면에서 매우 중요한 과정이다. 그러나 단일문서로부터 키워드를 추출해 내는 기존의 연구들은 정확도가 낮거나 한정된 분야에 대해서만 검증을 수행하여 결과를 신뢰하기 어려운 문제가 있었다. 따라서 본 연구에서는 정확하면서도 다양한 분야의 텍스트에 적용 가능한 키워드 추출 방법을 제시하고자 단어의 동시출현 정보와 그래프 모델을 바탕으로 TextRank 알고리즘을 변형한 새로운 형태의 알고리즘을 동시에 적용하는 키워드 추출 기법을 제안하였다. 제안한 기법을 활용하여 성능평가를 진행한 결과 기존의 연구들보다 향상된 정확도를 얻을 수 있음을 확인하였다.