• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.538-540
• /
• 2005

대화형 에이전트가 다양한 분야에서 적용됨에 따라서 현실성 있는 대화 생성을 위한 자연언어 생성에 대한 연구가 관심을 끌고 있다. 대화형 에이전트에서는 보통 미리 준비된 문장을 이용하여 사용자와 대화를 수행하지만, 최근에는 문장을 동적으로 생성하고 학습함으로써 보다 유연하고 현실성있는 서비스를 제공하는 대화형 에이전트가 활발히 연구되고 있다. 본 논문에서는 문장계획 트리를 인코딩 방법으로 적용한 대화형 유전자 프로그래밍을 통해 대화형 에이전트의 문장을 생성하는 방법을 제안한다. 피험자 12명을 대상으로 템플릿 기반 시스템과의 비교 실험결과, 제안하는 방법의 유용성을 확인할 수 있었다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.2
• /
• pp.119-128
• /
• 2006

As dialogue systems are widely required, the research on natural language generation in dialogue has raised attention. Contrary to conventional dialogue systems that reply to the user with a set of predefined answers, a newly developed dialogue system generates them dynamically and trains the answers to support more flexible and customized dialogues with humans. This paper proposes an evolutionary method for generating sentences using interactive genetic programming. Sentence plan trees, which stand for the sentence structures, are adopted as the representation of genetic programming. With interactive evolution process with the user, a set of customized sentence structures is obtained. The proposed method applies to a dialogue-based train booking agent and the usability test demonstrates the usefulness of the proposed method.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.3-7
• /
• 2018

본 연구진은 모든 형태소 분석 후보에 적절한 의존관계를 부여하여 구문분석 트리 후보를 순위화하여 제시하는 한국어 구문 분석 시스템 BCD-KL-Parser를 개발하고 있다. 이 시스템의 최종목표는 형태소 분석후보와 구문분석 트리 후보를 줄여나감으로써, 구문분석의 정확도와 실행 속도를 높이는 것이다. 본 논문에서 소개하는 BCD-KL-Parser에서는 형태적 중의성 해소규칙을 정의하여 형태소 분석후보의 수를 줄이고, 용언의 하위범주화 정보와 선택제약 정보 그리고 의존관계 제약규칙을 정의하여 구문분석 트리 후보의 수를 최소화할 수 있었다. 그 결과 '21세기 세종계획 구문분석 말뭉치'에서 무작위로 추출한 2,167문장에 대하여 UAS 92.27%를 달성할 수 있었다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.3
• /
• pp.64-70
• /
• 2004

Korean and Japanese have same structure of sentences because they belong to same family of languages. So, The transfer driven machine translation is most efficient to translate each other. This paper introduce a method which creates a transfer dictionary for Token Based Transfer Driven Koran-Japanese Machine Translation(TB-TDMT). If the transfer dictionaries are created well, we get rid of useless effort for traditional parsing by performing shallow parsing. The semi-parser makes the dependency tree which has minimum information needed output generating module. We constructed the transfer dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 900 utterances which are collected from travel planning domain. The success-ratio of our system is $92\%$ on restricted testing environment and $81\%$ on unrestricted testing environment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.4
• /
• pp.40-46
• /
• 1999

This paper introduce a Koran-Japanese machine translation system which is a module in the spoken language interpreting system It is implemented based on the TDMT(Transfre Driven Machine Translation). We define a new unit of translation so called TOKEN. The TOKEN-based translation method resolves nonstructural feature in Korean sentences and increases the quaity of translating results. In our system, we get rid of useless effort for traditional parsing by performing semi-parsing. The semi-parser makes the dependency tree which has minimum information needed generating module. We constructed the generation dictionaries by using the corpus obtained from ETRI spoken language database. Our system was tested with 600 utterances which is collected from travel planning domain The success-ratio of our system is 87% on restricted testing environment and 71% on unrestricted testing environment.