• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.229-236
• /
• 2003

Named entity recognition is the process indispensable to question answering and information extraction systems. This paper presents an HMM based named entity (m) recognition method using the construction principles of compound words. In Korean, many named entities can be decomposed into more than one word. Moreover, there are contextual relationships among nouns in an NE, and among an NE and its surrounding words. In this paper, we classify words into a word as an NE in itself, a word in an NE, and/or a word adjacent to an n, and train an HMM based on NE-related word types and parts of speech. Proposed named entity recognition (NER) system uses trigram model of HMM for considering variable length of NEs. However, the trigram model of HMM has a serious data sparseness problem. In order to solve the problem, we use multi-level back-offs. Experimental results show that our NER system can achieve an F-measure of 87.6% in the economic articles.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.6
• /
• pp.229-238
• /
• 2018

The rapid response of disaster accidents can be archived through the organical involvement of various disaster and safety control agencies. To define the terminology of disaster safety is essential for communication between disaster safety agencies and well as announcement for the public. Also, to efficiently construct a word dictionary of disaster safety terminology, it's necessary to define the priority of the terms. In order to establish direction of word dictionary construction, this paper compares the usage of disaster safety terminology by media: word dictionary, new media, and social media, respectively. Based on the terminology resources collected from each media, we visualized the distribution of terminology according to frequency weights and analyzed co-occurrence patterns. We also classified the types of terminology into four categories and proposed the priority in the construction of disaster safety word dictionary.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.17-27
• /
• 2012

Open Market is one of the key factors to accelerate the profit. Usually retailers sell items in several Open Market. One of the challenges for retailers is to assign categories of items with different classification systems. In this research, we propose an item category recommendation method to support appropriate products category registration. Our recommendations are based on semantic relation between existing and any other Open Market categorization. In order to analyze correlations of categories, we use Morpheme analysis, Korean Wiki Dictionary, WordNet and Google Translation API. Our proposed method recommends a category, which is most similar to a guide word by measuring semantic similarity. The experimental results show that, our system improves the system accuracy in term of search category, and retailers can easily select the appropriate categories from our proposed method.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.241-248
• /
• 2011

Homographs can have multiple senses. In order to understand the meaning of a sentence, it is necessary to identify which sense isused for each word in the sentence. Previous researches on this problem heavily relied on the word co-occurrence information. However, we noticed that in case of verbs, information about subordinating cases of verbs can be utilized to further improve the performance of word sense disambiguation. Different senses require different sets of subordinating cases. In this paper, we propose the verb sense disambiguation using subordinating case information. The case information acquire postposition features in Standard Korean Dictionary. Our experiment on 12 high-frequency verb homographs shows that adding case information can improve the performance of word sense disambiguation by 1.34%, from 97.3% to 98.7%. The amount of improvement may seem marginal, we think it is meaningful because the error ratio reduced to less than a half, from 2.7% to 1.3%.

• Interdisciplinary Bio Central
• /
• v.3 no.4
• /
• pp.14.1-14.9
• /
• 2011

Protein homology detection is an important issue in comparative genomics. Because of the exponential growth of sequence databases, fast and efficient homology detection tools are urgently needed. Currently, for homology detection, sequence comparison methods using local alignment such as BLAST are generally used as they give a reasonable measure for sequence similarity. However, these methods have drawbacks in offering overall sequence similarity, especially in dealing with eukaryotic genomes that often contain many insertions and duplications on sequences. Also these methods do not provide the explicit models for speciation, thus it is difficult to interpret their similarity measure into homology detection. Here, we present a novel method based on Word Conservation Score (WCS) to address the current limitations of homology detection. Instead of counting each amino acid, we adopted the concept of 'Word' to compare sequences. WCS measures overall sequence similarity by comparing word contents, which is much faster than BLAST comparisons. Furthermore, evolutionary distance between homologous sequences could be measured by WCS. Therefore, we expect that sequence comparison with WCS is useful for the multiple-species-comparisons of large genomes. In the performance comparisons on protein structural classifications, our method showed a considerable improvement over BLAST. Our method found bigger micro-syntenic blocks which consist of orthologs with conserved gene order. By testing on various datasets, we showed that WCS gives faster and better overall similarity measure compared to BLAST.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.1
• /
• pp.57-62
• /
• 2004

We have proposed an efficient method of word separation in a handwritten legal amount on bank check based on the spatial gaps between the connected components. The previous gap measures all suffer from the inherent problem of underestimation or overestimation that causes a deterioration in separation performance. In order to alleviate such burden, we have developed a modified version of each distance measure. Also, 4 class clustering based method of integrating three different types of distance measures has been proposed to compensate effectively the errors in each measure, whereby further improvement in performance of word separation is expected. Through a series of word separation experiments, we found that the modified distance measures show a better performance with over 2 - 3% of the word separation rate than their corresponding original distance measures. In addition, the proposed combining method based on 4-class clustering achieved further improvement by effectively reducing the errors common to two of three distance measures as well as the individual errors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.423-428
• /
• 2017

These days, various and tons of education information are rapidly increasing and spreading due to Internet and smart devices usage. Recently, as e-Learning usage increasing, many instructors and students (learners) need to set a goal to maximize learners' result of education and education system efficiency based on big data analytics via online recorded education historical data. In this paper, the author applied Word2Vec algorithm (neural network algorithm) to find similarity among education words and classification by clustering algorithm in order to objectively recognize and analyze online recorded education historical data. When the author applied the Word2Vec algorithm to education words, related-meaning words can be found, classified and get a similar vector values via learning repetition. In addition, through experimental results, the author proved the part of speech (noun, verb, adjective and adverb) have same shortest distance from the centroid by using clustering algorithm.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.901-909
• /
• 2015

In this paper, to build a parallel corpus between Korean and English in Wikipedia. We proposed a method to find similar sentences based on language resources and topic modeling. We first applied language resources(Wiki-dictionary, numbers, and online dictionary in Daum) to match word sequentially. We construct the Wiki-dictionary using titles in Wikipedia. In order to take advantages of the Wikipedia, we used translation probability in the Wiki-dictionary for word matching. In addition, we improved the accuracy of sentence similarity measuring method by using word distribution based on topic modeling. In the experiment, a previous study showed 48.4% of F1-score with only language resources based on linear combination and 51.6% with the topic modeling considering entire word distributions additionally. However, our proposed methods with sequential matching added translation probability to language resources and achieved 9.9% (58.3%) better result than the previous study. When using the proposed sequential matching method of language resources and topic modeling after considering important word distributions, the proposed system achieved 7.5%(59.1%) better than the previous study.

• Journal of the Korean Society of Safety
• /
• v.38 no.3
• /
• pp.69-76
• /
• 2023

The purpose of the rules on the Occupational Safety and Health Standards (hereafter safety and health rules) is to regulate the safety and health measures stipulated in the Occupational Safety and Health Act and the specific instructions necessary for their implementation. However, the safety and health rules are extensive and complexly connected, making navigation difficult for users. In order for users to readily access safety and health rules, this study analyzed the frequency, distribution, and significance of terms included in the overall rules. First, the term distribution index was created based on the frequency and distribution of words extracted through text mining. The term distribution index derives from whether a word appears only in a specific chapter or across all rules. This allows users to effectively explore terms to be followed in a specific working environment and terms to be complied with in the overall working environment. Next, the related words of the previously derived terms were visualized through t-SNE and the Word2Vec algorithm. This can help prioritize the things that need to be managed first, focusing on key terms without checking the overall rules. Moreover, this study can help users explore safety and health rules by allowing them to understand the distribution of words and visualize related terms.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.337-344
• /
• 2006

In this paper, we describe the design and the implementation of word clustering system using a definition of an entry word in the dictionary, called a dictionary definition. Generally word clustering needs various features like words and the performance of a system for the word clustering depends on using some kinds of features. Dictionary definition describes the meaning of an entry in detail, but words in the dictionary definition are implicative or abstractive, and then its length is not long. The word clustering using only features extracted from the dictionary definition results in a lots of small-size clusters. In order to make large-size clusters and improve the performance, we need to transform the features into more general words with keeping the original meaning of the dictionary definition as intact as possible. In this paper, we propose two methods for extending the dictionary definition using ontology. One is to extend the dictionary definition to parent words on the ontology and the other is to extend the dictionary definition to some words in fixed depth from the root of the ontology. Through our experiments, we have observed that the proposed systems outperform that without extending features, and the latter's extending method overtakes the former's extending method in performance. We have also observed that verbs are very useful in extending features in the case of word clustering.