• The KIPS Transactions:PartB
• /
• v.15B no.4
• /
• pp.365-374
• /
• 2008

In this paper, we propose a model to enrich an ontology by incrementally extending the relations through variations of patterns. In order to generalize initial patterns, combinations of features are considered as candidate patterns. The candidate patterns are used to extract relations from Wikipedia, which are sorted out according to reliability based on corpus frequency. Selected patterns then are used to extract relations, while extracted relations are again used to extend the patterns of the relation. Through making variations of patterns in incremental enrichment process, the range of pattern selection is broaden and refined, which can increase coverage and accuracy of relations extracted. In the experiments with single-feature based pattern models, we observe that the features of lexical, headword, and hypernym provide reliable information, while POS and syntactic features provide general information that is useful for enrichment of relations. Based on observations on the feature types that are appropriate for each syntactic unit type, we propose a pattern model based on the composition of features as our ongoing work.

• Journal of the Korean Society for Library and Information Science
• /
• v.46 no.1
• /
• pp.163-181
• /
• 2012

We investigated how useful video tags were in summarizing video speech and how valuable positional information was for speech summarization. Furthermore, we examined the similarity among sentences selected for a speech summary to reduce its redundancy. Based on such analysis results, we then designed and evaluated a method for automatically summarizing speech transcripts using a modified Maximum Marginal Relevance model. This model did not only reduce redundancy but it also enabled the use of social tags, title words, and sentence positional information. Finally, we compared the proposed method to the Extractor system in which key sentences of a video speech were chosen using the frequency and location information of speech content words. Results showed that the precision and recall rates of the proposed method were higher than those of the Extractor system, although there was no significant difference in the recall rates.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.466-475
• /
• 2003

To build an efficient Question-Answering (QA) system, a question type classifier is needed. It can classify user's queries into predefined categories regardless of the surface form of a question. In this paper, we propose a question type classifier using a Support Vector Machine (SVM). The question type classifier first extracts features like lexical forms, part of speech and semantic markers from a user's question. The system uses $X^2$ statistic to select important features. Selected features are represented as a vector. Finally, a SVM categorizes questions into predefined categories according to the extracted features. In the experiment, the proposed system accomplished 86.4% accuracy The system precisely classifies question type without using any rules like lexico-syntactic patterns. Therefore, the system is robust and easily portable to other domains.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.3
• /
• pp.289-304
• /
• 2006

The purpose of this pilot study is to construct a searching thesaurus with word association test in the library and information science field and to confirm it's functionality as searching aids through query expansion experiments. The test results were analyzed to four types of relationship between stimulus words and response words, and the terms of association thesaurus were compared with descriptors of an existing thesaurus. The test results show that the word association test is a fruitful method to identify many related terms and narrower and equivalent terms in some degree to the stimulus terms. Furthermore. in the query expansion experiment. the Performance of association thesaurus was better than that of an existing thesaurus, This result demonstrates that word association thesaurus can apply to query expansion.

• Korean Journal of Cognitive Science
• /
• v.15 no.1
• /
• pp.35-41
• /
• 2004

The letter delay task using monosyllabic words has been employed in order to investigate whether Korean word is processed by the phonological route, and to investigate which stage this phonological information affects word recognition. Two main conditions were delaying a sounding letter( $\rightarrow$향), and delaying a silent letter( $\rightarrow$양). Experiment 1 was the naming task with the SOAs of 150㎳ and 250㎳ in order to investigate whether the phonological information affects the early stages, or the later stages of word recognition. The results showed that the interaction between the phonological value condition and the presence/absence of the prime was significant under the 150㎳ SOA, but not under 250㎳ SOA. Experiment 2 was conducted in order to generalize the results of Experiment 1 in the lexical decision task. The results showed the similar pattern as the Experiment 1. These experiments indicate that Korean words are processed by the phonological route, and the phonological information plays roles in the early stages of word recognition.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2591-2599
• /
• 1998

In this paper, we proose a method of recognizing unknown words and correcting spelling errors(including spacing erors) to increase the performance of Korean information processing systems. Unknown words are recognized through comparative analysis of two or more morphologically similar eojeols(spacing units in Korean) including the same unknown word candidates. And spacing errors and spelling errors are corrected by using lexicatlized rules shich are automatically extracted from very large raw corpus. The extractionof the lexicalized rules is based on morphological and contextual similarities between error eojeols and their corection eojeols which are confirmed to be used in the corpus. The experimental result shows that our system can recognize unknown words in an accuracy of 98.9%, and can correct spacing errors and spelling errors in accuracies of 98.1% and 97.1%, respectively.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.73-79
• /
• 2010

Emotion intelligence computing is able to processing of human emotion through it's studying and adaptation. Also, Be able more efficient to interaction of human and computer. As sight and hearing, music & image is constitute of short time and continue for long. Cause to success marketing, understand-translate of humanity emotion. In this paper, Be design of check system that matched music and image by user emotion keyword(irritability, gloom, calmness, joy). Suggested system is definition by 4 stage situations. Then, Using music & image and emotion ontology to retrieval normalized music & image. Also, A sampling of image peculiarity information and similarity measurement is able to get wanted result. At the same time, Matched on one space through pared correspondence analysis and factor analysis for classify image emotion recognition information. Experimentation findings, Suggest system was show 82.4% matching rate about 4 stage emotion condition.

• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.21-27
• /
• 2005

본 논문에서는 국가에서 추진하는 차세대신성장동력산업과 관련된 특정 분야('바이오 신약/장기' 분야 중 '면역 기능 제어')를 선택하여, 기구축된 면역학 전문용어사전을 비롯하여 의학용어사전, 표준국어대사전 등을 참조하여 핵심 용어와 관련 용어를 중심으로 면역학 시소러스(어휘 3,462개) 및 온톨로지(개념 노드 4,703개)를 구축하였다. 이것은 전문용어사전부터 온톨로지에 이르기까지 통일화된 표준 체계를 가지고 있으며, 도메인 온톨로지를 구축하여 향후 온톨로지 개발 방향을 설정할 수 있는 계기가 되었다고 할 수 있다. 또한 면역학 시소러스는 검색의 성능을 향상시킬 수 있도록 충분한 양의 데이터를 구축하였고 면역학 온톨로지는 언어처리적 관점에서의 온톨로지를 표현하였다. 이는 정보검색에서의 효율성을 비롯하여, 특정 웹 온톨로지 언어를 이용한 웹 온톨로지로의 변환성, 대규모 도메인 온톨로지라는 점에서 의미를 가진다고 할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.875-878
• /
• 2007

Up until now, when a user search product information, the keyword-based search that mainly uses frequency of words or vocabulary information has been utilized in large. In the keyword-based research, the user should have to bear additional burden in order to search the displayed results manually once again because it shows those files that have no connection at all with the inquiries made by the user. To resolve such a problem, ontology has been emerged. In this paper, product search system using ontology was constructed directly and also tested how accurate search it does perform through the searching according to classification. To test this, about 40,000 product data of A discount store, which was operating on/off line discount stores, were constructed as database, and developmental environment for User Interface was tested by having developed the search system using JSP and PowerBuilder 9.0. Results from the test proved that the search method using Domain Ontology for product presented and designed in this paper was superior to the existing keyword-based search method.

• Journal of Service Research and Studies
• /
• v.2 no.2
• /
• pp.45-51
• /
• 2012

U-healthcare is real-time monitoring of personal biometric information using by portable devices, home network and information and communication technology based healthcare systems, and fused together automatically to overcome the constraints of time and space are connected with hospitals and doctors. As u-healthcare gives health service in anytime and anywhere, it becomes to be a new type of medical services in patients management and disease prevention. In this paper, recent changes in prevention-oriented care is analyzed in becoming early response for Healthcare Information System by requirements analysis for technology development trend. According to the healthcare system, PACS, OCS, EMR and emergency medical system, U-healthcare is presenting the design of a patient-centered integrated client system. As the relationship between the meaning of the terms is used in the ontology, information models in the system is providing a common vocabulary with various levels of formality. In this paper, we propose an ontology-based system for patient-centered services, including the concept of clustering to clustering the data to define the relationship between these ontologies for more systematic data.