• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.54-62
• /
• 2009

To avoid the redundant investment on the project selection process, it is necessary to check whether the submitted research topics have been proposed or carried out at other institutions before. This is possible through the search engines adopted by the keyword matching algorithm which is based on boolean techniques in national-sized research results database. Even though the accuracy and speed of information retrieval have been improved, they still have fundamental limits caused by keyword matching. This paper examines implemented TFIDF-based algorithm, and shows an experiment in search engine to retrieve and give the order of priority for similar and redundant documents compared with research proposals, In addition to generic TFIDF algorithm, feature weighting and K-Nearest Neighbors classification methods are implemented in this algorithm. The documents are extracted from NDSL(National Digital Science Library) web directory service to test the algorithm.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.152-159
• /
• 2010

Existing character recognition algorithm recognize characters in simple conditional. It has the disadvantage that recognition rates often drop drastically when input document image has low quality, rotated text, various font or size text because of external noise or data loss. In this paper, proposes the optical character recognition algorithm which using bicubic interpolation method for the catalog retrieval when the input image has rotated text, blurred, various font and size. In this paper, applied optical character recognition algorithm consist of detection and recognition part. Detection part applied roberts and hausdorff distance algorithm for correct detection the catalog of book. Recognition part applied bicubic interpolation to interpolate data loss due to low quality, various font and size text. By the next time, applied rotation for the bicubic interpolation result image to slant proofreading. Experimental results show that proposal method can effectively improve recognition rate 6% and search-time 1.077s process result.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1397-1403
• /
• 2015

A named entity(NE) dictionary is an important resource for the performance of NE recognition. However, it is not easy to construct a NE dictionary manually since human annotation is time consuming and labor-intensive. To save construction time and reduce human labor, we propose a semi-automatic system for the construction of a NE dictionary. The proposed system constructs a pseudo-document with Wiki-categories per NE class by using an active learning technique. Then, it calculates similarities between Wiki entries and pseudo-documents using the BM25 model, a well-known information retrieval model. Finally, it classifies each Wiki entry into NE classes based on similarities. In experiments with three different types of NE class sets, the proposed system showed high performance(macro-average F1-score of 0.9028 and micro-average F1-score 0.9554).

• Journal of Information Management
• /
• v.23 no.1
• /
• pp.39-62
• /
• 1992

In this paper about 60 auxiliary words and 320 stopwords are selected from analysis of sample data, four types of stop word are classified left, right and - auxiliary word truncation & normal. And a keyword extraction system is suggested which undertakes efficient truncation of auxiliary word from words, conversion of Chinese word to Korean and exclusion of stopword. The selected keyeords in this system show 92.2% of accordance ratio compared with manually selected keywords by expert. And then compound words consist of $4{\sim}6$ character generate twice of additional new words and 58.8% words of those are useful as keyword.

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.367-376
• /
• 2002

XML allows users to define elements using arbitrary words and organize them in a nested structure. These features of XML offer both challenges and opportunities in information retrieval and document management. In this paper, we propose a new methodology for computing similarity considering XML semantics - meanings of the elements and nested structures of XML documents. We generate extended-element vectors, using thesaurus, to normalize synonyms, compound words, and abbreviations and build similarity matrix using them. And then we compute similarity between XML elements. We also discover and minimize XML structure using automata(NFA(Nondeterministic Finite Automata) and DFA(Deterministic Finite automata). We compute similarity between XML structures using similarity matrix between elements and minimized XML structures. Our methodology considering XML semantics shows 100% accuracy in identifying the category of real documents from on-line bookstore.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.766-772
• /
• 2007

As XML is widely used, many researches on the XML storage and query processing have been done. But, previous works on path query processing have mainly focused on the storage and retrieval methods for a large XML document or XML documents had a same DTD. Those researches did not efficiently process partial match queries on the differently-structured document set. To resolve the problem, we suggested a new index structure using relational table. The method constructs the $B^+$-tree index using backward label paths instead of forward label paths used in previous researches for storing path information and allows for finding the label paths that match the partial match queries efficiently using it when process the queries.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.7
• /
• pp.831-836
• /
• 2002

There are various information resources on the Internet and people are taking more interest in XML day by day. In XML, the structure of information can be freely defined so that the standardization of documents can be hardly made. If DTD, which is applied to an XML Document representing specific information, is including concept information, it can be freely applied to the structure of document and also contributes to the convenience in information retrieval. In this study, we developed universal DTD Generator in order to automatically generate DTD including concept information. For the generation of universal DTD, the conceptualization of information is required; to conceptualize information, the hierarchical structuring and propertizing are required. The hierarchical structuring represents the inclusive relation of routine concepts for representing information in hierarchical structure, and the propertizing represents the property and mutual relation that the each concept represented in hierarchical structure can have. The defined hierarchical structure and propertization come to generate the universal DTD Generator. The universal DTD generated by DTD Generator can be applied to all the XML Documents representing the same information in different structure. However, the most ideal way is that the information of universal DTD, which can be applied to various documents, is including all the cases. Therefore, the study for designing correct concept information is necessary.

• Journal of Korea Multimedia Society
• /
• v.1 no.1
• /
• pp.1-17
• /
• 1998

Video information is an important component of multimedia systems such as Digital Library, World-Wide Web (WWW), and Video-On-Demand (VOD) service system. Video information has hierarchical document structure inherently, so it is named "structure video document" in this paper. This paper proposes a data model, a query language, and an indexing scheme for structured video documents in order to store, retrieve, and share video documents efficiently. In representing structured video documents, the object-oriented data modeling technique is used since the hierarchical structure information can be modeled as complex objects. We also define object types for the structure information. Our query language supports not only content-based retrieval, which means the queries based on the structure of video documents, and spatial/temporal relation for video documents. In order to perform structure queries efficiently, as well as to reduce the storage overhead of indices, an optimized inverted index structure is proposed.

• Journal of KIISE:Software and Applications
• /
• v.27 no.7
• /
• pp.691-701
• /
• 2000

Software documents consists of a number of objects and relationships between them, and structure of documents can be changed frequently. In this paper, we propose a version storage and consistency management model for fine-grained software objects based on operations applied to edit software objects. An object has an interface and can be updated only through operations defined in its interface. Operations applied to objects are recorded in the operation history, which is used to retrieve versions of a document and manage consistency between documents. Because versions of an object are stored and retrieved using the operation delta, it is not needed to compare versions of a document to extract delta and it is easy to identify the changes between versions in order to propagate the changes. Consistencies between documents are managed using dependencies between objects and kinds of the operations applied to the objects. Therefore unnecessary version propagation can be avoided. This paper presents a formal model of version retrieval and consistency management at the fine-grained level based on operations applied to the objects.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.902-909
• /
• 2016

Question answering system (QA system) is a system that finds an actual answer to the question posed by a user, whereas a typical search engine would only find the links to the relevant documents. Recent works related to the open domain QA systems are receiving much attention in the fields of natural language processing, artificial intelligence, and data mining. However, the prior works on QA systems simply replace all words that are not in the training data with a single token, even though such unseen words are likely to play crucial roles in differentiating the candidate answers from the actual answers. In this paper, we propose a method to compute vectors of such unseen words by taking into account the context in which the words have occurred. Next, we also propose a model which utilizes inverse document frequencies (IDF) to efficiently process unseen words by expanding the system's vocabulary. Finally, we validate that the proposed method and model improve the performance of a QA system through experiments.