• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.3
• /
• pp.192-200
• /
• 2012

In order for humans and robots to interact in daily life, robots need to understand human speech and link it to their actions. This paper proposes a hierarchical behavior model for robot action control using natural language commands. The model, which consists of episodes, primitive actions and atomic functions, uses a sentential cognitive system that includes multiple modules for perception, action, reasoning and memory. Human speech commands are translated to sentences with a natural language processor that are syntactically parsed. A semantic parsing procedure was applied to human speech by analyzing the verbs and phrases of the sentences and linking them to the cognitive information. The cognitive system performed according to the hierarchical behavior model, which consists of episodes, primitive actions and atomic functions, which are implemented in the system. In the experiments, a possible episode, "Water the pot," was tested and its feasibility was evaluated.

• Korean Journal of Cognitive Science
• /
• v.3 no.2
• /
• pp.291-309
• /
• 1992

The computer manipulation by means of natural language prcessing will be not only helpful to use the computer with more simple and more comfortable but also flexiable to communicate between human and computers.In this paper the natural language interfaces will be applied to an intelligent geography tutoring systems(IGTS),and we will inspect the something to consider in the case of its implementation.Each module of IGTS is connected to the interface module and correspondence with each other for the sake of natural conversation between system and learner.

• Language and Information
• /
• v.17 no.2
• /
• pp.51-66
• /
• 2013

Korean is a wh-in-situ language where the wh-expression stays in situ with an obligatory Q-particle marking its interrogative scope. This paper briefly reviews some basic properties of the wh-question construction in Korean and shows how a typed feature structure grammar, HPSG (Pollard and Sag 1994, Sag et al. 2003), together with the notions of 'type hierarchy' and 'constructions', can provide a robust basis for parsing the wh-construction in the language. We show that this system induces robust syntactic structures as well as enriched semantic representations for real-time applications such as machine translation, which require deep processing of the phenomena concerned.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2002.02a
• /
• pp.28-35
• /
• 2002

Automatic identification of Chinese personal names in unrestricted texts is a key task in Chinese word segmentation, and can affect other NLP tasks such as word segmentation and information retrieval, if it is not properly addressed. This paper (1) demonstrates the problems of Chinese personal name identification in some If applications, (2) analyzes the structure of Chinese personal names, and (3) further presents the relevant processing strategies. The geographical differences of Chinese personal names between Beijing and Hong Kong are highlighted at the end. It shows that variation in names across different Chinese communities constitutes a critical factor in designing Chinese personal name Identification algorithm.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.9
• /
• pp.1111-1118
• /
• 2004

Natural language query is the best user interface for the users of web text retrieval systems. This paper proposes a retrieval system with expanded keyword from syntactically-analyzed structures of user's natural language query based on natural language processing technique. Through the steps combining or splitting the compound nouns based on syntactic tree traversal, and expanding the other-formed or shorten-formed keyword into multiple keyword, it shows that precision and correctness of the retrieval system was enhanced.

• Korean Management Science Review
• /
• v.17 no.3
• /
• pp.147-160
• /
• 2000

These days, a modeling tool or environment has to know about the others on the market and build bridges to them with which their customers insist on sharing models and data. When it is based on a closed architecture, a tangle of import/export point translators is required. Using an exchange standard, we can design an open architecture for the interchange of models and data. XML(Extensible Markup Language) provides a framework for describing the syntax for creating and exchanging data structures. The explosive growth of XML-based business proposals and standards reflects the urgent requirements and its strength. This paper proposes an XML-based language for sharing decision models within the MSOR/DSS community. The language is able to allow applications and on-line analytic processing tools to models obtained from multiple sources without having to deal with individual differences between those sources. It is expected to be a medium for B2B integration by supporting flexible interchange of decision models.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.159-163
• /
• 1998

다국어 대화체 번역 시스템은 미국의 카네기 멜론 대학과 일본의 ATR 및 한국의 전자통신연구원 등이 가입한 CSTAR의 99년 국제간 음성언어번역 시스템 데모를 위한 한국어측 번역 시스템이다. CSTAR-IF는 국제간 데모를 위해 각 국의 시스템끼리 주고 받는 정보의 단위 혹은 형태로서, 중간언어 표현의 한 가지 방법으로 간단하면서도 단순한 표현으로 특정 영역 내에 나타나는 의미를 표현할 수 있도록 정의되었다. 다국어 번역 시스템은 크게 두 가지로 나누어진다. 하나는 한국어 음성인식 결과를 IF로 변환하는 해석 시스템이고, 다른 하나는 IF로부터 한국어 문장을 생성하여 음성으로 들려주는 생성 시스템이다. 한국어 해석 시스템은 현재 92%의 해석 성공률을, 생성 시스템은 98%의 생성 성공률을 보이고 있다.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.675-677
• /
• 2018

의존 구문 분석은 문장 구조를 중심어와 수식어로 이루어진 의존 관계로 표현하는 방법이다. 표현 방식이 간단하고 자유 어순에 적합하기 때문에 한국어와 같이 어순이 자유롭고 문장 성분의 생략이 빈번한 언어에 적합한 것으로 알려져 있다. 본 논문에서는 한국어 의존 구문 분석 연구를 활성화하기 위해 개최된 2018 국어 정보 처리 시스템 경진대회에서 사용된 학습 및 평가 데이터를 간략히 소개하고, 각 참가자들이 제출한 시스템의 결과를 요약한다.

• Journal of the military operations research society of Korea
• /
• v.10 no.2
• /
• pp.33-41
• /
• 1984

Hangout programming language, written in Hangout and having syntax of Korean, can enhance readability very much for its naturalness, and is suited for Hangout data processing. But there exist several problems in implementing it due to the peculiarities of Korean such as verb position, variation of termination. This paper proposes a solution for implementing Hangeul high level language and introduces a Hangout programming language HANSFOR (Hangout Structured Fortran), implemented according to the proposed method. HANSFOR satisfies such requirements of Hangout high level language as mentioned above and can handle Korean and Chinese character data efficiently. Especially, though it is based on Fortran, it is free-formatted and provides structured programming concept to compensate for defects of original Fortran. It is successfully implemented on NEC S/100.