• Journal of KIISE:Software and Applications
• /
• v.37 no.2
• /
• pp.129-136
• /
• 2010

In this paper, we present an Example-based Dialogue System for English conversation tutoring. It aims to provide intelligent one-to-one English conversation tutoring instead of old fashioned language education with static multimedia materials. This system can understand poor expressions of students and it enables green hands to engage in a dialogue in spite of their poor linguistic ability, which gives students interesting motivation to learn a foreign language. And this system also has educational functionalities to improve the linguistic ability. To achieve these goals, we have developed a statistical natural language understanding module for understanding poor expressions and an example-based dialogue manager with high domain scalability and several effective tutoring methods.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.4
• /
• pp.43-50
• /
• 2004

Multi-lingual query answering system is the system which answers on the queries with several languages. LASSO[l] is the system that aims to answer the multi-lingual query. In this paper, we design and implement a Korean analysis system for LASSO. The Korean analysis system for query answering needs processing techniques of dialogue style. And the system must be practical and general so as to use on various domains. This system uses not dialogue processing techniques with high cost and low utility but heuristic rules with low cost and high utility. It is designed and implemented as a Korean interface of multi-lingual query answering system. The techniques of this system highly contribute to information retrieval and Korean analysis researches.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.111-115
• /
• 2017

목적 지향적 대화 시스템(Goal-oriented dialogue system)은 텍스트나 음성을 통해 특정한 목적을 수행할 수 있는 시스템이다. 최근 RNN(recurrent neural networks)을 기반으로 대화 데이터를 end-to-end learning 방식으로 학습하여 대화 시스템을 구축하는데에 활용한 연구가 있다. End-to-end 방식의 학습은 도메인에 대한 지식 없이 학습 데이터 자체만으로 대화 시스템 구축을 위한 학습이 가능하다는 장점이 있지만 도메인 지식을 학습하기 위해서는 많은 양의 데이터가 필요하다는 단점이 존재한다. 이에 본 논문에서는 도메인 특정 지식을 결합하여 end-to-end learning 방식의 학습이 가능한 Hybrid Code Network 구조를 기반으로 한국어로 구성된 식당 예약에 관련한 대화 데이터셋을 이용하여 식당 예약을 목적으로하는 대화 시스템을 구축하는 방법을 제안한다. 실험 결과 본 시스템은 응답 별 정확도 95%와 대화 별 정확도 63%의 성능을 나타냈다.

• MALSORI
• /
• no.67
• /
• pp.103-120
• /
• 2008

Basic components for multimodal interface, such as speech recognition, speech synthesis, gesture recognition, and multimodal fusion, have their own technological limitations. For example, the accuracy of speech recognition decreases for large vocabulary and in noisy environments. In spite of those technological limitations, there are lots of applications in which speech-oriented multimodal user interfaces are very helpful to users. However, in order to expand application areas for speech-oriented multimodal interfaces, we have to develop the interfaces focused on usability. In this paper, we introduce usability and user-centered design methodology in general. There has been much work for evaluating spoken dialogue systems. We give a summary for PARADISE (PARAdigm for Dialogue System Evaluation) and PROMISE (PROcedure for Multimodal Interactive System Evaluation) that are the generalized evaluation frameworks for voice and multimodal user interfaces. Then, we present usability components for speech-oriented multimodal user interfaces and usability testing guidelines that can be used in a user-centered multimodal interface design process.

• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.283-289
• /
• 2004

조응어 해석(Anaphora Resolution)은 여러 응용 분야에 적절히 적용됨으로써 자연어 이해에서의 양적. 질적 향상을 가져 올 수 있다. 구어에서 조응어(anaphor)는 화자와 청자간에 공유된 정보를 간략하게 나타내는 형태이다. 특히, 구어를 주된 사용 언어로 하는 대화 시스템에서의 조응어의 양상을 살피고 해석하는 문제는 인간과 기계간의 의사소통(man-machine communication)을 온전히 하는 과제이다. 이 논문에서는 인간과 기계간의 대화 시스템(man-machine dialogue system)에서 흔히 쓰일 수 있는 조응 표현에 중점을 두어 그 유형을 살피고 해석의 방식을 제시하도록 한다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.399-403
• /
• 2023

본 논문에서는 다중 문서 기반의 대화 시스템을 통한 효율적인 정보 검색과 응답 생성에 중점을 둡니다. 대규모 데이터 집합에서 정확한 문서를 선택하는 데 필요한 검색의 중요성을 강조하며, 현재 검색 방법의 한계와 문제점을 지적합니다. 또한 더 자연스러운 답변을 생성하기 위해 대규모 언어 모델을 사용하게 되면서 fine-tuning 시에 발생하는 제약과 낭비를 모델의 제로샷 생성 능력을 활용하여 개선하려는 방안을 제안하며, 모델의 크기와 자원의 효율성에 대한 고려사항을 논의합니다. 우리의 접근 방식은 대규모 언어 모델을 프롬프트와 함께 다중 문서로 학습 없이 정보를 검색하고 응답을 생성하는 방향으로 접근하여 대화 시스템의 효율성과 유용성을 향상시킬 수 있음을 제시합니다.

• 한국ITS학회:학술대회논문집
• /
• v.2006 no.10
• /
• pp.286-289
• /
• 2006

• Journal of the Korea Convergence Society
• /
• v.9 no.12
• /
• pp.33-38
• /
• 2018

Recently, we are trying to predict the emotion from various information and to convey the emotion information that the supervisor wants to inform the audience. In addition, audiences intend to understand the flow of emotions through various information of non-dialogue parts, such as cinematography, scene background, background sound and so on. In this paper, we propose to extract emotions by mixing not only the context of scripts but also the cinematography information such as color, background sound, composition, arrangement and so on. In other words, we propose an emotional prediction system that learns and distinguishes various emotional expression techniques into dialogue and non-dialogue regions, contributes to the completeness of the movie, and quickly applies them to new changes. The precision of the proposed system is improved by about 5.1% and 0.4%, and the recall is improved by about 4.3% and 1.6%, respectively, when compared with the modified n-gram and morphological analysis.

• Knowledge Management Research
• /
• v.9 no.4
• /
• pp.65-75
• /
• 2008

Knowledge workers' workload to register knowledge can cause quality defects in the quality as well as the quantity of knowledge that must be accumulated in a knowledge management system(KMS). To enhance the availability of a KMS by acquiring more quality-guaranteed knowledge, autonomous knowledge acquisition which outdoes the automated acquisition must be initiated. Adopting the capabilities of context-awareness and inference in the field of context-aware computing, this paper intends to autonomously identify and acquire knowledge from knowledge workers' daily lives. Based on knowledge workers' context information, such as location, identification, schedule, etc, a methodology to monitor, sense, and gather knowledge that resides in their ordinary discussions is proposed. Also, a prototype systems of the context-based knowledge acquisition system(CKAS), which autonomously dictates, analyzes, and stores dialogue-based knowledge is introduced to prove the validity of the proposed concepts. This paper's methodology and prototype system can support relieving knowledge workers' burden to manually register knowledge, and hence provide a way to accomplish the goal of knowledge management, efficient and effective management of qualified knowledge.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.213-222
• /
• 2019

Determining the meaning of a keyword in a speech dialogue system is an important technology for the future implementation of an intelligent speech dialogue interface. After extracting keywords to grasp intention from user's utterance, the intention of utterance is determined by using the semantic mark of keyword. One keyword can have several semantic marks, and we regard the task of attaching the correct semantic mark to the user's intentions on these keyword as a problem of word sense disambiguation. In this study, about 23% of all keywords in the corpus is manually tagged to build a semantic mark dictionary, a synonym dictionary, and a context vector dictionary, and then the remaining 77% of all keywords is automatically tagged. The semantic mark of a keyword is determined by calculating the context vector similarity from the context vector dictionary. For an unregistered keyword, the semantic mark of the most similar keyword is attached using a synonym dictionary. We compare the performance of the system with manually constructed training set and semi-automatically expanded training set by selecting 3 high-frequency keywords and 3 low-frequency keywords in the corpus. In experiments, we obtained accuracy of 54.4% with manually constructed training set and 50.0% with semi-automatically expanded training set.