• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.170-175
• /
• 2022

일반적으로 대규모 언어 모델들은 다량의 데이터를 오랜시간 사전학습하면서 레이블을 예측하기 위한 성능을 높여왔다. 최근 언어 모델의 레이블 예측에 대한 정확도가 높아지면서, 언어 모델이 왜 해당 결정을 내렸는지 이해하기 위한 신뢰도 높은 Natural Language Explanation(NLE) 을 생성하는 것이 시간이 지남에 따라 주요 요소로 자리잡고 있다. 본 논문에서는 높은 레이블 정확도를 유지하면서 동시에 언어 모델의 예측에 대한 신뢰도 높은 explanation 을 생성하는 참신한 자연어 추론 시스템을 제시한 Natural-language Inference over Label-specific Explanations(NILE)[1] 을 소개하고 한국어 데이터셋을 이용해 NILE 과 NLE 를 활용하지 않는 일반적인 자연어 추론 태스크의 성능을 비교한다.

• Proceedings of the CALSEC Conference
• /
• 2005.03a
• /
• pp.55-61
• /
• 2005

We will introduce a new web-based knowledge management system in progress, in which XML-based web information extraction and our structuring knowledge technologies are combined using ontology-based natural language processing. Our aim is to provide efficient access to heterogeneous information on the web, enabling users to use a wide range of textual and non textual resources, such as newspapers and databases, effortlessly to accelerate knowledge acquisition from such knowledge sources. In order to achieve the efficient knowledge management, we propose at first an XML-based Web information extraction which contains a sophisticated control language to extract data from Web pages. With using standard XML Technologies in the system, our approach can make extracting information easy because of a) detaching rules from processing, b) restricting target for processing, c) Interactive operations for developing extracting rules. Then we propose a structuring knowledge system which includes, 1) automatic term recognition, 2) domain oriented automatic term clustering, 3) similarity-based document retrieval, 4) real-time document clustering, and 5) visualization. The system supports integrating different types of databases (textual and non textual) and retrieving different types of information simultaneously. Through further explanation to the specification and the implementation technique of the system, we will demonstrate how the system can accelerate knowledge acquisition on the Web even for novice users of the field.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.109-126
• /
• 2022

The number and variety of products and services offered by companies have increased dramatically, providing customers with more choices to meet their needs. As a solution to this information overload problem, the provision of tailored services to individuals has become increasingly important, and the personalized recommender systems have been widely studied and used in both academia and industry. Existing recommender systems face important problems in practical applications. The most important problem is that it cannot clearly explain why it recommends these products. In recent years, some researchers have found that the explanation of recommender systems may be very useful. As a result, users are generally increasing conversion rates, satisfaction, and trust in the recommender system if it is explained why those particular items are recommended. Therefore, this study presents a methodology of providing an explanatory function of a recommender system using a review text left by a user. The basic idea is not to use all of the user's reviews, but to provide them in a summarized form using only reviews left by similar users or neighbors involved in recommending the item as an explanation when providing the recommended item to the user. To achieve this research goal, this study aims to provide a product recommendation list using user-based collaborative filtering techniques, combine reviews left by neighboring users with each product to build a model that combines text summary methods among deep learning-based natural language processing methods. Using the IMDb movie database, text reviews of all target user neighbors' movies are collected and summarized to present descriptions of recommended movies. There are several text summary methods, but this study aims to evaluate whether the review summary is well performed by training the Sequence-to-sequence+attention model, which is a representative generation summary method, and the BertSum model, which is an extraction summary model.

• English Language & Literature Teaching
• /
• v.9 no.2
• /
• pp.173-192
• /
• 2003

The purpose of this paper is to analyze the semantic ambiguity of coordination connected by 'and' in English and show a clear explanation for the meaning of the sentence. Two sentences which are connected by 'and' can be divided into the symmetric conjunction and the asymmetric conjunction according to its meaning. Especially, in order to explain the different meaning in the asymmetric conjunctions, we introduce the theory of presupposition and entailment, which provides the solution to the ambiguity in meaning. It can be said that presupposition and entailment can logically explain the meaning of natural language.

• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.149-164
• /
• 2008

Our limited understanding of real-life music information queries is an impediment to developing music information retrieval (MIR) systems that meet the needs of real users. This study aims to contribute to developing a theorized understanding of how people seek music information by an empirical investigation of real-life queries, in particular, focusing on the accuracy of user-provided information and users' uncertainty expressions. This study found that much of users' information is inaccurate; users made various syntactic and semantic errors in providing this information. Despite these inaccuracies and uncertainties, many queries were successful in eliciting correct answers. A theory from pragmatics is suggested as a partial explanation for the unexpected success of inaccurate queries.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.25 no.1
• /
• pp.56-62
• /
• 1988

Artificial Intelligence(AI) is that branch of computer science that deals with designing computer system that exhibit some of the characteristics associated with intelligence on human behaviors such as, understanding natural language, reasoning, solving problems, robotics and so on. The most developed component of artificial intelligence today is probably the expert system. An expert system is defined as a computer program that embodies organized knowledge concerning some specific domain of human expertise and programmed to perform convincingly as an advisory consultant in the given domain with self-explanation of reasoning on demand. This paper describes general concept of artificial intelligence and expert system and investigates applicability of expert system to ship design.

• Communications of Mathematical Education
• /
• v.28 no.1
• /
• pp.45-55
• /
• 2014

Lacan gives an explanation on our real actual world by the concepts the "Real", the "Imaginary" and the "Symbolic". Although this three registers are not far from each other, they never can be unified. Among animals, only human has interest in the "truth". The concept of truth is discussed and debated in several contexts, including philosophy and religion. Many human activities depend upon the concept, which is assumed rather than a subject of discussion, including science, law, and everyday life. Language and words are a means by which humans convey information to one another, and the method used to determine what is a "truth" is termed a criterion of truth. Accepting then that "language is the basic social institution in the sense that all others presuppose language", Lacan found in Ferdinand de Saussure's linguistic division of the verbal sign between signifier and signified a new key to the Freudian understanding that "his therapeutic method was 'a talking cure'". The purpose of this paper is to understand Lacan's psychology and psychoanalysis by using the mathematical concepts and mathematical models, especially geometrical and topological models. And re-explanation of the symbolic model and symbols can help students understand new ideas and concepts in the educational scene.

• Korean Journal of Logic
• /
• v.17 no.2
• /
• pp.253-287
• /
• 2014

In First-Order Logic the English expressions, 'any', 'every', 'all', and 'each' are treated on a par but have different meanings in the natural language usages. Especially the expression 'any' is typically used only in the negative contexts, which linguists have paid attention to and attempted to provide an adequate explanation of. I shall show that the explanations so far mainly from linguists are not satisfactory and revive the philosophical insights concerning the logical features of 'any' provided by Zeno Vendler in 1962. I shall claim that the expression 'any' has what Vendler calls the 'freedom of choice' as its primary meaning and denotes what Kit Fine calls an 'arbitrary object'. It will be shown that the logical features of 'any' are manifested more evidently in the analysis of the Korean expression 'amwu'. I believe that this analysis has significant philosophical implications. As an instance I shall show that we can take a fresh perspective on the problem which involves the universal generalization rule and the preface paradox.

• Journal of Korean Elementary Science Education
• /
• v.42 no.1
• /
• pp.178-193
• /
• 2023

The aim of this study was to investigate differences in the achievement standards from the 2015 to the 2022 revised national science curriculum and to present the implications for science teaching under the revised curriculum. Achievement standards relevant to primary science education were therefore extracted from the national curriculum documents; conceptual domains in the two curricula were analyzed for differences; various kinds of centrality were computed; and the Louvain algorithm was used to identify clusters. These methods revealed that, in the revised compared with the preceding curriculum, the total number of nodes and links had increased, while the number of achievement standards had decreased by 10 percent. In the revised curriculum, keywords relevant to procedural skills and behavior received more emphasis and were connected to collaborative learning and digital literacy. Observation, survey, and explanation remained important, but varied in application across the fields of science. Clustering revealed that the number of categories in each field of science remained mostly unchanged in the revised compared with the previous curriculum, but that each category highlighted different skills or behaviors. Based on those findings, some implications for science instruction in the classroom are discussed.