Korean Wikipedia Research Articles

Building a Knowledge Base for QA System by Linking Korean Vocabulary and Wikipedia

For a QA system it's very important to have a notion of vocabulary used in questions and for building correct answers. Especially, when a word represents a concept, one can use related lexical instances to understand it and further extend the knowledge by using the associated information. In this work, we suggest a process of building a knowledge base for such concepts as people, organizations, and places, and linking their instances to Wikipedia articles. We also develop a workbench for KB building. This workbench should efficiently support all features needed to collect necessary data and build the knowledge base. We have created 150,941 links to Korean Wikipedia for 2,394 instances of Korean vocabulary. This KB can be used in QA systems to extend questions, while the workbench can be used to build the KB itself.

A study for categorizing relations between headword and aliases

ABSTRACTIn this study, we propose a method of categorizing relations between a headword and its aliases using Korean Wikipedia data. We propose orthographically similar types and orthographically different types. Orthographically similar types are divided into 5 types: Word space, Pronunciation difference, Omission, Abbreviation, and Word order change while different types are also classified into 4 types: Foreign word, Acronym, Paraphrased expression and Call name. We show examples to verify the proposed method.

커널 Ripple-Down Rule을 이용한 태깅 말뭉치 오류 자동 수정

Annotated Corpus is important to understand natural language using machine learning method. In this paper, we propose a new method to automate error reduction of annotated corpora. We use the Ripple-Down Rules(RDR) for reducing errors and Kernel to extend RDR for NLP. We applied our system to the Korean Wikipedia and blog corpus errors to find the annotated corpora error type. Experimental results with various views from the Korean Wikipedia and blog are reported to evaluate the effectiveness and efficiency of our proposed approach. The proposed approach can be used to reduce errors of large corpora.

언어자원 자동 구축을 위한 위키피디아 콘텐츠 활용 방안 연구

Abstract Various linguistic knowledge resources are required in order that machine can understand diverse variation in natural languages. This paper aims to devise an automatic construction method of linguistic resources by reflecting characteristics of online contents toward continuous expansion. Especially we focused to build NE(Named-Entity) dictionary because the applicability of NEs is very high in linguistic analysis processes. Based on the investigation on Korean Wikipedia, we suggested an efficient construction method of NE dictionary using the syntactic patterns and structural features such as metadatas. Key Words : Linguistic Resource Construction, Wikipedia, Named-Entity Dictionary, Knowledge Construction, Utilization of online contents * 본 연구는 2014년도 전북대학교 연구기반 조성비 지원에 의하여 연구되었음Received 17 March 2015, Revised 22 April 2015Accepted 20 May 2015Corresponding Author: Bo-Hyun Yun (Dept. of Computer Science Education, Mokwon University) Email: ybh@mokwon.ac.krⒸ The Society of Digital Policy & Management. All rights reserved. This is an open-access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0), which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is ISSN: 1738-1916 properly cited.

개체중의성해소에서 의미관련도 활용 효과 분석: 한국어 위키피디아를 사용하여

Abstract Entity linking is to link entity's name mentions occurring in t ext to corresponding entities within knowledge bases. Since the same entity mention may refer to different entities according to their context, entity linking needs to deal with entity disambiguation. Most recent works on entity disambiguation focus on semantic related-ness between entities and attempt to integrate semantic related ness with entity prior probabilities and term co-occurrence. To the best of my knowledge, however, it is hard to find studies that analyze and present the pure effects of semantic relatedness on entity disambiguation. From the experimentation on Korean Wikipedia da-ta set, this article empirically evaluates entity disambiguation approaches using semantic relatedness in terms of the following aspects: (1) the difference among semantic relatedness measures such as NGD, PMI, Jaccard, Dice,Simpson, (2) the influence of ambiguities in co-occurring entity mentions' set, and (3) the difference between in-dividual and collective disambiguation approaches.Key Words : Entity Linking, Entity Disambiguation, Semantic Relatedness, WikipediaReceived: Nov. 5, 2014Revised : Feb. 16, 2015Accepted: Mar. 10, 2015

음성 합성 시스템의 품질 향상을 위한 한국어 문장 기호 전처리 시스템

본 논문에서는 한국어 문장 기호의 처리를 통해 자연스러운 음성 합성 결과를 생성하는 방법에 대해서 논의한다. 이를 위해 한국어 위키피디아 문서를 분석하여 문장 기호의 사용을 8가지 형태로 분류하고, 11개의 정규표현식 규칙으로 문장 기호를 처리하는 방안을 제시한다. 그 결과 63,000 문장에 대해 56%의 정확도와 71.45%의 재현율을 달성하였으며, 문장 기호 처리 결과를 SSML 기반의 음성 합성 표현으로 변환하여 음성 합성 결과의 품질을 향상시키는 방법을 제안한다. In this paper, we propose a Korean sentence symbol preprocessor for a SSML (speech synthesis markup language) supported speech synthesis system in order to improve the quality of the synthesized result. After the analysis of Korean Wikipedia documents, we propose 8 categories for the meaning of sentence symbols and 11 regular expression for the classification of each category. After the development of a Korean sentence symbol preprocess system we archived 56% of precision and 71.45% of recall ratio for 63,000 sentences.

듀이십진분류법의 지역 보조표에서 한국 지역 구분의 수정 전개 방안에 관한 연구

본 연구는 십진분류법인 DDC, UDC, KDC, NDC의 지역구분 보조표의 구조와 그 안에서 한국 지리 구분 전개에 관해 비교 분석하고 각각의 분류표 안에서 지역구분 보조표의 번호와 분류항목명을 기술하고 그 특징을 논하였으며 서로 다른 십진식 분류표에서 지역 구분과 관련하여 공통적인 사항과 차별화되는 사항을 조사하였다. 또한 위키 백과와 한국의 행정 구역 분류도 조사하여 십진식 분류법과 다르게 한국을 구분하는 기준을 살펴보았다. 이러한 분석을 바탕으로 한국에 관한 지역구분의 전개가 가장 적게 이루어진 DDC를 중심으로 좀 더 상세한 전개 방안을 기본 원칙과 임의조항과 함께 제시하였으며 향후 십진분류법 개정에 있어서 참고가 되도록 하였다.