• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.127-132
• /
• 2008

This study proposes a Natural Language Query Framework (NLQF) for the semantic web. It supports an intelligent inference at a semantic level. Most of previous researches focused on the knowledge representation on the semantic web. However, to revitalize the intelligent e-business on the semantic web, there is a need for semantic level inference to the web information. To satisfy the need, we will review the knowledge/resource representation on the semantic web such as RDF, Ontology and Conceptual Graph (CG), and then discuss about the natural language (NL) inference. The result of this research could support a natural interface for the semantic web. Furthermore, we expect that the NLQF can be used in the semantic web-based business communications.

• 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.

• Spatial Information Research
• /
• v.7 no.2
• /
• pp.191-207
• /
• 1999

Data and information necessary for solving the spatial decision making problems are imperfect or inaccurate and most are described by natural language. In order to process these arts of information by the computer, the obscure linguistic value need to be described quantitatively to let and computer understand natural language used by humans. For this , the fuzzy set theory and the fuzzy logic are used representative methodology. So this paper describes the construction of the language model by the natural language that user easily can understand and the logical concepts and construction process for building the fuzzy inference mechanism. It makes possible to solve the space related decision making problems intellectually through structuring and inference used by the computer, in case of the evaluation concern or decision making problems are described inaccurate, based on the inaccurate or indistinct data and information.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.579-582
• /
• 2003

In this paper, we propose a 4-step inference method needed for constructing a natural language communication system. The method is used to obtain fuzzy quantifier Q′when QA is Fisr τ⇔ Q′(m′A) is mF is m"is τ is inferred (Q, Q′: quantifiers, A: fuzzy subject, m′, m": modifiers, y: fuzzy predicate, τ: truth qualifier). We show that Q′is resolved step by step for two types of Q, including a non-increasing type (few,...) and a non-decreasing type(most,...).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.4
• /
• pp.554-561
• /
• 2010

As a fundamental knowledge source in a global learning environment, it is feasible to apply the relational database management systems (RDBMS), object-oriented database management systems (OODBMS), and other traditional DBMS. However, the traditional DBMSs are not feasible in semantic knowledge/ontology representation and inference. One of the reasonable ways to overcome the limitations is the semantic web-based business support framework. Especially, in this study, we focused on the development of semantic web ontology and natural language (NL)-based inference framework. To validate the efficiency of the proposed framework, we considered a reasonable scenario for course recommendation in a university.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.12
• /
• pp.2406-2412
• /
• 2007

Recently, there are many researches about natural language processing programs using artificial intelligence methods. But the researches mostly concentrate on Korean morphological analyses and there are few researches about application of the results of Korean morphological analyses. In this paper, we implemented a natural language conversation program that NPC in games can talk with users by natural language sentences using the results of morphological analyses and a rule-based inference method. We proposed representation and implementation methods of rules suitable for the processing of natural language conversation using NEO, a rule-based inference engine. In the experiment using rules and facts about knowledge of conversation for diet counselor NPC, we could verify that natural conversation results were produced.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.189-192
• /
• 2007

This study proposes a Natural Language Query Framework (NLQF) on the semantic web to support the intelligent deduction at semantic level. A large number of former researches are focused on the knowledge representation on the semantic web. However, to revitalize the intelligent agent (IA)-based automated e-business contract with human customers, there is a need for semantic level approach to the web information. To enable accessing web information at semantic level, this paper discusses the pattern of complex natural language processing at first, and then the semantic web-based natural language inference in e-business environment. The NL-based approach could help the IAs on the web to communicate with customers and other IAs with more natural interface than traditional HTML-based web information. Therefore, our proposed NLQF will be used in semantic web-based intelligent e-business contracts between customers and IAs.

• Genomics & Informatics
• /
• v.10 no.4
• /
• pp.266-270
• /
• 2012

Grammatical inference methods are expected to find grammatical structures hidden in biological sequences. One hopes that studies of grammar serve as an appropriate tool for theory formation. Thus, we have developed JSequitur for automatically generating the grammatical structure of biological sequences in an inference framework of string compression algorithms. Our original motivation was to find any grammatical traits of several cancer genes that can be detected by string compression algorithms. Through this research, we could not find any meaningful unique traits of the cancer genes yet, but we could observe some interesting traits in regards to the relationship among gene length, similarity of sequences, the patterns of the generated grammar, and compression rate.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.12
• /
• pp.1639-1648
• /
• 1988

This paper deals with an analyzing method of the Korean syntax to implement a natural language understanding system. A matrix of the syntactic structure is derived by the structural features of the Korean language. The modificatoty and conceptual structures are extracted from the matrix and the predicate logic form is expressed by extracting the phrase, clause and conceptual structure in the analyzing process. This logic form constructs an knowledge base of the sentence and proposes the possibility of the inference.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.352-357
• /
• 2023

자연어 추론은 두 문장(전제, 가설)간의 관계를 이해하고 추론하여 함의, 모순, 중립 세 가지 범주로 분류하며, 전제-가설-라벨(PHL) 데이터셋을 활용하여 자연어 추론 모델을 학습한다. 그러나, 새로운 도메인에 자연어 추론을 적용할 경우 학습 데이터가 존재하지 않거나 이를 구축하는 데 많은 시간과 자원이 필요하다는 문제가 있다. 본 논문에서는 자연어 추론을 위한 학습 데이터인 전제-가설-라벨 삼중항을 자동 생성하기 위해 [1]에서 제안한 문장 변환 규칙 대신에 거대 언어 모델과 Chain-of-Thought(CoT), Program-aided Language Models(PaL) 등의 프롬프팅(Prompting) 방법을 이용하여 전제-가설-라벨 삼중항을 자동으로 생성하는 방법을 제안한다. 실험 결과, CoT와 PaL 프롬프팅 방법으로 자동 생성된 데이터의 품질이 기존 규칙이나 기본 프롬프팅 방법보다 더 우수하였다.