• Annual Conference on Human and Language Technology
• /
• 2005.10a
• /
• pp.1-6
• /
• 2005

텍스트 기반 문서의 급증으로 인해 정보 추출 기술이 더욱 중요해지고 있다 특히 최근에 활발한 연구가 진행되고 있는 개체 간 관계 추출 기술은 정보검색과 질의응답 등 많은 분야에 걸쳐 활용될 수 있는 기술이다 본 논문은 기존의 자질 기반 관계 추출 시스템의 재현율을 향상시키기 위해 WHISK 알고리즘을 도입한 시스템에 관한 것이다. WHISK 알고리즘은 문장으로부터 관계에 참여하는 개체 쌍을 추출하는 규칙을 자동으로 학습한다. 그리고 시스템은 최대 엔트로피 모델을 이용하여 WHISK에 의해 추출된 개체 쌍에 적합한 관계 유형을 파악해 낸다. 본 논문은 시스템에 사용된 WHISK 알고리즘과 최대 엔트로피 모델에 대해서 알아보고, 실제로 WHISK 알고리즘을 도입하여 관계를 가지는 개체 쌍을 추출하여 문제를 해결했을 때 어느 정도의 성능 향상이 있는지 알아본다.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.92-97
• /
• 2002

의미기반 정보 검색, 자연어 질의 응답, 지식 자동 습득, 담화 처리 등 높은 수준의 자연언어처리 시스템에서 의미처리를 위한 대용량의 지식 베이스가 필요하다. 이러한 지식 베이스 중에서 가장 기본적인 것이 워드넷이다. 이러한 워드넷을 이용함으로써 여러 의미 사이의 의미 유사도를 구할 수 있고, 속성을 물려받을 수 있기 때문에 비슷한 속성을 가진 의미들을 한꺼번에 다루는 데 유용하다. 본 논문에서는 기본 어휘를 바탕으로 기존의 명사 워드넷과 단일어 사전을 이용하여 한국어 동사 워드넷을 구축하는 방법을 제시한다. 본 논문에서 1차 작업을 통하여 구축한 동사 워드넷에는 동사 1,757개에 대한 4,717개의 의미(중복을 포함하면 모두 5,235개의 의미)를 포함하고 있으며 특별히 의미가 많이 편중된 14개의 개념에 속한 571개의 의미를 53개의 세부 개념으로 재분류하여 최종적으로 모두 767개의 계층적 개념으로 구성된 동사 워드넷이 만들어 졌다.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.85-93
• /
• 2003

This paper proposes an item based learning system using e-mail in order to motivate learners effectively and avoid the bottleneck problem under highly competitive access situations such as the traditional web based learning. The proposed system has th ree features as follows: first, through e-mail, a learner receives test items depending on his/her level, submit an answer sheet, and then identify an assessment with help messages. Secondly, on the web, an instructor easily constructs item database without any other tools and monitors the status of each learner by identifying the learners' record. Finally, an easy-to-use interaction mechanism enhances the inter-activity between learners and instructors, and the usability of Q&A(Question and Answer) service by incorporating e-mail into the web bulletin board.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.333-337
• /
• 2015

In this paper, we suggest a Coreference Resolution system for Korean using Mention Pair with SVM. The system introduced in this paper, also be able to extract Mention from document which is including automatically tagged name entity information, dependency trees and POS tags. We also built a corpus, including 214 documents with Coreference tags, referencing online news and Wikipedia for training the system and testing the system's performance. The corpus had 14 documents from online news, along with 200 question-and-answer documents from Wikipedia. When we tested the system by corpus, the performance of the system was extracted by MUC-F1 55.68%, B-cube-F1 57.19%, and CEAFE-F1 61.75%.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.469-476
• /
• 2001

As the service of information through web system increases in modern society, many questions and consultations are going on through Home page and E-mail in the hospital. But there are some burdens for the management and postponements for answering the questions. In this paper, we investigate the document classification methods as a primary research of the auto-answering system. On the basis of 1200 documents which are questions of patients, 66% are used for the learning documents and 34% for test documents. All of are also used for the document classification using NBC (Naive Bayes Classifier), common words and coefficient of correlation. As the result of the experiments, the two methods proposed in this paper, that is, common words and coefficient of correlation are higher as much as 3% and 5% respectively than the basic NBC methods. This result shows that the correlation between indexes and categories is more effective than the word frequency in the document classification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.43-51
• /
• 1996

Fuzzy rules in fuzzy logic control play a major role in deciding the control dynamics of a fuzzy logic controller. Thus, control performance is mainly determined by the quality of fuzzy rules. This paper introduces an optimization method for fuzzy rules using GAS with adaptive probabilies of crossover and mutation. Also we design two fitness measures to satisfy control objectives by partitioning the response of a plant into two parts. An initial population is generated by an automatic fuzzy rule generation method instead of random selection for fast a.pproaching to the final solution. We employed a nonlinear plant to simulate our method. It is shown through simulation that our method is reasonable and can be useful for optimizing fuzzy rules.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3577-3588
• /
• 1999

This paper describes design and implementation of a general purpose cyber educational system. In this system, there are different types of menus and services according to such user's rights as system operators, professors, assistant instructors, students. In order to keep in close contact between students and professors, provided are various services such as the official announcement, transcripts of lecture, bulletin board, Q/A corner, report box, archive of study materials, electronic mail box, memorandum including checking of one's attendance and school record. For the purpose of activating small group studies and discussion about given subject, it can organize into groups automatically and provide with debating rooms. The system is implemented by separating with both HTML design and programming part by templete concept. Overload of iterative server is solved by adjusting the numbers of DB servers of each service.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.7
• /
• pp.285-292
• /
• 2014

A named entity recognition method is used to improve the performance of information retrieval systems, question answering systems, machine translation systems and so on. The targets of the named entity recognition are usually PLOs (persons, locations and organizations). They are usually proper nouns or unregistered words, and traditional named entity recognizers use these characteristics to find out named entity candidates. The titles of books, movies and TV programs have different characteristics than PLO entities. They are sometimes multiple phrases, one sentence, or special characters. This makes it difficult to find the named entity candidates. In this paper we propose a method to quickly extract title named entities from news articles and automatically build a named entity dictionary for the titles. For the candidates identification, the word phrases enclosed with special symbols in a sentence are firstly extracted, and then verified by the SVM with using feature words and their distances. For the classification of the extracted title candidates, SVM is used with the mutual information of word contexts.

• Korean Journal of Cognitive Science
• /
• v.26 no.3
• /
• pp.263-278
• /
• 2015

Online Q&A for the National Institute of the Korean Language provides expert's answers for questions about the Korean language, in which many similar questions are repeatedly posted like other Q&A boards. So, if a system automatically finds questions that are similar to a user's question, it can immediately provide users with recommendable answers to their question and prevent experts from wasting time to answer to similar questions repeatedly. In this paper, we set 5 classes of questions based on its topic which are frequently asked, and propose to classify questions to those classes. Our system searches similar questions by combining topic similarity, vector similarity and sequence similarity. Experiment shows that our method improves search correctness with topic classification. In experiment, Mean Reciprocal Rank(MRR) of our system is 0.756, and precision for the first result is 68.31% and precision for top five results is 87.32%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.451-461
• /
• 2024

Recently, various AI chatbots based on large language models have been released. Chatbots have the advantage of providing users with quick and easy information through interactive prompts, making them useful in various fields such as question answering, writing, and programming. However, a vulnerability in chatbots called "prompt injection attacks" has been proposed. This attack involves injecting instructions into the chatbot to violate predefined guidelines. Such attacks can be critical as they may lead to the leakage of confidential information within large language models or trigger other malicious activities. However, the vulnerability of Korean prompts has not been adequately validated. Therefore, in this paper, we aim to generate malicious Korean prompts and perform attacks on the popular chatbot to analyze their feasibility. To achieve this, we propose a system that automatically generates malicious Korean prompts by analyzing existing prompt injection attacks. Specifically, we focus on generating malicious prompts that induce harmful expressions from large language models and validate their effectiveness in practice.