• Smart Media Journal
• /
• v.5 no.3
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.3
• /
• pp.336-340
• /
• 2008

Sentiment classification is a recent subdiscipline of text classification, which is concerned not with the topic but with opinion. In this paper, we present a Korean sentence and document classification system using effective sentiment features. Korean sentiment classification starts from constructing effective sentiment feature sets for positive and negative. The synonym information of a English word thesaurus is used to extract effective sentiment features and then the extracted English sentiment features are translated in Korean features by English-Korean dictionary. A sentence or a document is represented by using the extracted sentiment features and is classified and evaluated by SVM(Support Vector Machine).

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1254-1271
• /
• 2018

Keyphrase extraction is one of fundamental natural language processing (NLP) tools to improve many text-mining applications such as document summarization and clustering. In this paper, we propose to use two novel techniques on the top of the state-of-the-art keyphrase extraction methods. First is the anti-patterns that aim to recognize non-keyphrase candidates. The state-of-the-art methods often used the rich feature set to identify keyphrases while those rich feature set cover only some of all keyphrases because keyphrases share very few similar patterns and stylistic features while non-keyphrase candidates often share many similar patterns and stylistic features. Second one is to use the dependency graph instead of the word co-occurrence graph that could not connect two words that are syntactically related and placed far from each other in a sentence while the dependency graph can do so. In experiments, we have compared the performances with different settings of the graphs (co-occurrence and dependency), and with the existing method results. Finally, we discovered that the combination method of dependency graph and anti-patterns outperform the state-of-the-art performances.

• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1347-1359
• /
• 2005

We propose an efficient block classification of the document images using the second-order statistical texture features computed from spatial gray level dependence matrix (SGLDM). We studied on the techniques that will improve the block speed of the segmentation and feature extraction speed and the accuracy of the detailed classification. In order to speedup the block segmentation, we binarize the gray level image and then segmented by applying smoothing method instead of using texture features of gray level images. We extracted seven texture features from the SGLDM of the gray image blocks and we applied these normalized features to the BP (backpropagation) neural network, and classified the segmented blocks into the six detailed block categories of small font, medium font, large font, graphic, table, and photo blocks. Unlike the conventional texture classification of the gray level image in aerial terrain photos, we improve the classification speed by a single application of the texture discrimination mask, the size of which Is the same as that of each block already segmented in obtaining the SGLDM.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.

• The KIPS Transactions:PartB
• /
• v.12B no.6 s.102
• /
• pp.697-702
• /
• 2005

The focused crawler is a topic-driven document-collecting crawler that was suggested as a promising alternative of maintaining up-to-date web document Indices in search engines. A major problem inherent in previous focused crawlers is the liability of missing highly relevant documents that are linked from off-topic documents. This problem mainly originated from the lack of consideration of structural information in a document. Traditional weighting method such as TFIDF employed in document classification can lead to this problem. In order to improve the performance of focused crawlers, this paper proposes a scheme of locality-based document segmentation to determine the relevance of a document to a specific topic. We segment a document into a set of sub-documents using contextual features around the hyperlinks. This information is used to determine whether the crawler would fetch the documents that are linked from hyperlinks in an off-topic document.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.117-140
• /
• 2013

Hindi is the most widely spoken language in India, with more than 300 million speakers. As there is no separation between the characters of texts written in Hindi as there is in English, the Optical Character Recognition (OCR) systems developed for the Hindi language carry a very poor recognition rate. In this paper we propose an OCR for printed Hindi text in Devanagari script, using Artificial Neural Network (ANN), which improves its efficiency. One of the major reasons for the poor recognition rate is error in character segmentation. The presence of touching characters in the scanned documents further complicates the segmentation process, creating a major problem when designing an effective character segmentation technique. Preprocessing, character segmentation, feature extraction, and finally, classification and recognition are the major steps which are followed by a general OCR. The preprocessing tasks considered in the paper are conversion of gray scaled images to binary images, image rectification, and segmentation of the document's textual contents into paragraphs, lines, words, and then at the level of basic symbols. The basic symbols, obtained as the fundamental unit from the segmentation process, are recognized by the neural classifier. In this work, three feature extraction techniques-: histogram of projection based on mean distance, histogram of projection based on pixel value, and vertical zero crossing, have been used to improve the rate of recognition. These feature extraction techniques are powerful enough to extract features of even distorted characters/symbols. For development of the neural classifier, a back-propagation neural network with two hidden layers is used. The classifier is trained and tested for printed Hindi texts. A performance of approximately 90% correct recognition rate is achieved.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.99-118
• /
• 2023

The objective of this study is to identify performance factors in the automatic classification of records by utilizing metadata that contains the contextual information of records. For this study, we collected 97,064 records of original textual information from Korean central administrative agencies in 2022. Various classification algorithms, data selection methods, and feature extraction techniques are applied and compared with the intent to discern the optimal performance-inducing technique. The study results demonstrated that among classification algorithms, Random Forest displayed higher performance, and among feature extraction techniques, the TF method proved to be the most effective. The minimum data quantity of unit tasks had a minimal influence on performance, and the addition of features positively affected performance, while their removal had a discernible negative impact.

• Asia pacific journal of information systems
• /
• v.29 no.1
• /
• pp.35-49
• /
• 2019

The paper attempts to document the application of relevant Machine Learning (ML) models on Yelp (a crowd-sourced local business review and social networking site) dataset to analyze, predict and recommend business. Strategically using two cloud platforms to minimize the effort and time required for this project. Seven machine learning algorithms in Azure ML of which four algorithms are implemented in Databricks Spark ML. The analyzed Yelp business dataset contained 70 business attributes for more than 350,000 registered business. Additionally, review tips and likes from 500,000 users have been processed for the project. A Recommendation Model is built to provide Yelp users with recommendations for business categories based on their previous business ratings, as well as the business ratings of other users. Classification Model is implemented to predict the popularity of the business as defining the popular business to have stars greater than 3 and unpopular business to have stars less than 3. Text Analysis model is developed by comparing two algorithms, uni-gram feature extraction and n-feature extraction in Azure ML studio and logistic regression model in Spark. Comparative conclusions have been made related to efficiency of Spark ML and Azure ML for these models.

• Journal of the Korean Society for Library and Information Science
• /
• v.53 no.2
• /
• pp.179-199
• /
• 2019

In this paper, we propose optimal methodologies for classifying patent literature by examining various feature extraction methods, machine learning and deep learning models, and provide optimal performance through experiments. We compared the traditional BoW method and a distributed representation method (word embedding vector) as a feature extraction, and compared the morphological analysis and multi gram as the method of constructing the document collection. In addition, classification performance was verified using traditional machine learning model and deep learning model. Experimental results show that the best performance is achieved when we apply the deep learning model with distributed representation and morphological analysis based feature extraction. In Section, Class and Subclass classification experiments, We improved the performance by 5.71%, 18.84% and 21.53%, respectively, compared with traditional classification methods.