• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.

• The Korean Journal of Applied Statistics
• /
• v.12 no.2
• /
• pp.585-591
• /
• 1999

Warner(1965)의 확률화 응답 모형을 두 번 연속사용하여 응답자들이 일관성 있는 응답을 했다는 가설을 검정하는 검정통계량을 제안했다. 이것은 양측과 단측 대립가설 모두 검정하는데 이용할 수 있으며, 제안된 검정통계량의 조건분포는 정규분포에 근사한다. 이 검정통계량의 조건부 검정력 함수와 비조건부 검정력 함수를 구하였다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 1994.02a
• /
• pp.143-152
• /
• 1994

• Kyungpook Mathematical Journal
• /
• v.56 no.1
• /
• pp.121-123
• /
• 2016

In this paper, we compute the number of distinct centralizers and commutativity degree of a class of finite groups. These computations produce a further class of examples of groups answering one question raised by Belcastro and Sherman and another one raised by Lescot.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.116-121
• /
• 2017

cQA(Community-based Question Answering) 시스템은 온라인 커뮤니티를 통해 사용자들이 질문을 남기고 답변을 작성할 수 있도록 만들어진 시스템이다. 신규 질문이 인입되면, 기존에 축적된 cQA 저장소에서 해당 질문과 가장 유사한 질문을 검색하고, 그 질문에 대한 답변을 신규 질문에 대한 답변으로 대체할 수 있다. 하지만, 키워드 매칭을 사용하는 전통적인 검색 방식으로는 문장에 내재된 의미들을 이용할 수 없다는 한계가 있다. 이를 극복하기 위해서는 의미적으로 동일한 문장들로 학습이 되어야 하지만, 이러한 데이터를 대량으로 확보하기에는 어려움이 있다. 본 논문에서는 질문이 제목과 내용으로 분리되어 있는 대량의 cQA 셋에서, 질문 제목과 내용을 의미 벡터 공간으로 사상하고 두 벡터의 상대적 거리가 가깝게 되도록 학습함으로써 의사(pseudo) 유사 의미의 성질을 내재화 하였다. 또한, 질문 제목과 내용의 의미 벡터 표현(representation)을 위하여, semi-training word embedding과 CNN(Convolutional Neural Network)을 이용한 딥러닝 기법을 제안하였다. 유사 질문 검색 실험 결과, 제안 모델을 이용한 검색이 키워드 매칭 기반 검색보다 좋은 성능을 보였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.1
• /
• pp.1-8
• /
• 2007

When confronted with a query, question answering systems endeavor to extract the most exact answers possible by determining the answer type that fits with the key terms used in the query. However, the efficacy of such systems is limited by the fact that the terms used in a query may be in a syntactic form different to that of the same words in a document. In this paper, we present an efficient semantic query expansion methodology based on query patterns in a question category concept list comprised of terms that are semantically close to terms used in a query. The proposed system first constructs a concept list for each question type and then builds the concept list for each question category using a learning algorithm. The results of the present experiments suggest the promise of the proposed method.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.470-475
• /
• 2004

In this paper, we propose a method to extract a definitional answer sentence for a Definitional Question-Answering System. definitional answer sentence patterns are manually constructed with restriction rules to patterns, and a ranking information of the pattern using its frequency from the corpus. answer sentence pattern consists of the syntactic structure of a definitional answer sentence, and clue words. this system show 83% accuracy for untrained corpus.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.476-482
• /
• 2004

Question-Answering (QA) system has to analyze user's intention correctly to respond correct answer for user's question., This paper proposes a focus-word-based question analysis approach for Korean QA system to analyze user's intention correctly. focus-word is a clue-word which selects question type. The question type is determined to one in 75 subcategories using semantics of focus-words. the proposed system accomplished 97.18% accuracy for the main category and 95.31% accuracy for the subcategory in the question classification.

• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.41-51
• /
• 2002

In this paper, I describe a knowledge-based question-answering system and significance of the system with a view to constructing a fact database. The knowledge-based system takes advantage of existing NLP-resources such as conceptual structures of ontologies along with morphotogical, syntactic and semantic analysis. The use of conceptual structures allows us to select right answers through inferences basically made by expansions of concepts. However, the work of constructing factual knowledge requires a great amount of acquisition time in large-scale applications because of the nature of human interference. This is why the procedure of acquiring factual knowledge cannot be fully automated. Apart from efficiency considerations. the knowledge-based system deserves serious consideration, I point out benefits of the system and describe the whole procedure of building the system in terms of a fact database.

• Journal of the Korean Society for information Management
• /
• v.21 no.4 s.54
• /
• pp.251-263
• /
• 2004

For question-answering system, question analysis module finds the question points from user's natural language questions, classifies the question types, and extracts some useful information for answer. This paper proposes a question type classifying technique based on focus words extracted from questions and word semantic information, instead of complicated rules or huge knowledge resources. It also shows how to find the question type without focus words, and how useful the synonym or postfix information to enhance the performance of classifying module.