• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.479-488
• /
• 2006

The iconic language interlace is designed to provide more convenient environments for communication to the target system than the keyboard-based interface. For this work, tendencies and features of vocabulary are analyzed in conversation corpora constructed from the corresponding domains with high degree of utilization, and the meaning and vocabulary system of iconic language are constructed through application of natural language processing methodologies such as morphological, syntactic and semantic analyses. The part of speech and grammatical rules of iconic language are defined in order to make the situation corresponding the icon to the vocabulary and meaning of the Korean language and to communicate through icon sequence. For linguistic ambiguity resolution which may occur in the iconic language and for effective semantic processing, semantic data focused on situation of the iconic language are constructed from the general purpose Korean semantic dictionary and subcategorization dictionary. Based on them, the Korean language generation from the iconic interface in semantic domain is suggested.

• The Journal of the Korea Contents Association
• /
• v.17 no.2
• /
• pp.96-104
• /
• 2017

As new smart devices are evolved into the intelligent agent who can reflect user intention and use context, user experience design for easy and convenient usability becomes a core competitive edge. Under the assumption that human centered natural interaction is necessary for the optimal smart TV experience, this study explores the types of voice interaction which are peculiar to TV watching context. In order to build a model for the users to naturally interact with Smart TV, conversation patterns were collected by requesting key features of Smart TV to intelligent agent. Collected sentences were applied to CfA model and classified by responses to activate features. The classified conversation patterns were divided into feature activation and information search. This study has identified that CfC1 occurred when voice interaction between Smart TV and users was vague and CfC2 occurred when the requests were complex or conditional. In conclusion, Simple Request Type is the most efficient model and voice interaction is more appropriate to use to clarify users' vague requests.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2021

Spoken language understanding, which aims to understand utterance as naturally as human would, are mostly focused on English language. In this paper, we construct a Korean language dataset for spoken language understanding, which is based on a conversational corpus between reservation system and its user. The domain of conversation is limited to restaurant reservation. There are 7 types of slot tags and 5 types of intent tags in 6857 sentences. When a model proposed in English-based research is trained with our dataset, intent classification accuracy decreased a little, while slot filling F1 score decreased significantly.

• The Journal of the Korea Contents Association
• /
• v.5 no.4
• /
• pp.122-132
• /
• 2005

CVE(Collaborative Virtual Environment) is the virtually shared area where people cannot come together physically, but wish to discuss, collaborate on, or even dispute certain matters. In CVEs, in habitants are usually represented by humanoid embodiments, generally referred to as avatars. But most current graphical CVE systems fail to reflect the natural relationship between the avatar's gesture and the conversation that is taking place. More than 65% of the information exchanged during a person to person conversation is carried on the nonverbal band. Therefore, it is expected to be beneficial to provide such communication channels in CVEs in some way. To address this issue, this study proposes a scheme to represent avatar's gestures that can support the CVE users' communication. In the first level, this study classifies the non-verbal communication forms that can be applicable to avatar gesture design. In the second level, this study categorizes the body language according to the types of interaction with verbal language. And in the third level, this study examines gestures with relevant verbal expressions according to the body parts-from head to feet. One bodily gesture can be analyzed in the description of gesture representation, the meaning of gesture and the possible expressions, which can be used in gestural situation.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.31-34
• /
• 2018

대화 시스템에서 사람과 기계와의 모든 발화에서 발생하는 상황들을 모두 규칙화할 수 없기 때문에 자연스러운 대화가 단절되는 breakdown 현상이 빈번하게 일어날 수 있다. 이런 현상이 발생하는 이유는 다음과 같다. 첫째, 대화에서는 다양한 도메인이 등장하기 때문에 시스템이 커버할 수 있는 리소스가 부족하며, 둘째, 대화 데이터에서 학습을 위한 annotation되어 있는 많은 양의 코퍼스를 보유하기에는 한계가 있으며, 모델에 모든 대화 흐름의 히스토리를 반영하기 어렵다. 이런 한계점이 존재함에도 breakdown detection은 자연스러운 대화 시스템을 위해서는 필수적인 기능이다. 본 논문은 이런 이슈들을 해소하기 위해서 memory attention기반의 새로운 모델을 제안하였다. 제안한 모델은 대화내에 발화에 대해 memory attention을 이용하여 과거 히스토리가 반영되기 때문에 자연스러운 대화흐름을 잘 detection할 수 있으며, 기존 모델과의 성능비교에서 state-of-the art 결과를 도출하였다.

• Journal of Information Technology Applications and Management
• /
• v.30 no.4
• /
• pp.11-28
• /
• 2023

This paper proposes a method of integrating ChatGPT with traditional chatbot systems to enhance conversational artificial intelligence(AI) and create more efficient conversational systems. Traditional chatbot systems are primarily based on classification models and are limited to intent classification and simple response generation. In contrast, ChatGPT is a state-of-the-art AI technology for natural language generation, which can generate more natural and fluent conversations. In this paper, we analyze the business service areas that can be integrated with ChatGPT and traditional chatbots, and present methods for conducting conversational scenarios through case studies of service types. Additionally, we suggest ways to integrate ChatGPT with traditional chatbot systems for intent recognition, conversation flow control, and response generation. We provide a practical implementation example of how to integrate ChatGPT with traditional chatbots, making it easier to understand and build integration methods and actively utilize ChatGPT with existing chatbots.

• Speech Sciences
• /
• v.13 no.4
• /
• pp.187-200
• /
• 2006

The speech synthesis technology is widely used and its application area is also being broadened to an automatic response service, a learning system for handicapped person, etc. However, the sound quality of the speech synthesizer has not yet reached to the satisfactory level of users. To make a synthesized speech, the existing synthesizer generates rhythms only by the interval information such as space and comma or by several punctuation marks such as a question mark and an exclamation mark so that it is not easy to generate natural rhythms of people even though it is based on mass speech database. To make up for the problem, there is a way to select rhythms after processing language from a higher level information. This paper proposes a method for generating tags for controling rhythms by analyzing the meaning of sentence with speech situation information. We use the Systemic Functional Grammar (SFG) [4] which analyzes the meaning of sentence with speech situation information considering the sentence prior to the given one, the situation of a conversation, the relationship among people in the conversation, etc. In this study, we generate Semantic Speech Control Tag (SSCT) by the result of SFG's meaning analysis and the voice wave analysis.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.158-165
• /
• 2022

Journal of Convergence for Information Technology. This study explores how native speakers (NSs) and non-native speakers (NNSs) of English negotiate meanings during conversational interactions to achieve successful communication. This study involved 40 participants: 20 native English speakers and 20 Korean university students. The participants were divided into 20 pairs, with each pair consisting of one NS and one NNS. Tasks for conversation were given and the execution recorded in order to collect data. 37 recorded conversations were transcribed and used for analysis, including statistical analyses. Results showed that both NSs and NNSs mutually put in effort for successful communication. While NSs mostly played the role of leading the natural flow of the conversation, encouraging their non-native interlocutors to speak, NNSs used various strategies to compensate for their lack of linguistic competence in the target language. NNSs employed a wide range of communicative strategies to keep the conversation going. The results of this study contribute to a better understanding of interactions between NSs and NNSs and yield pedagogical implications.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.138-147
• /
• 2022

Recently, chatbots have been applied in various fields and have shown good results, and many attempts to use chatbots in shopping mall product recommendation services are being conducted on e-commerce platforms. In this paper, for a conversation system that recommends a fashion that a user wants based on conversation between the user and the system and fashion image information, a transformer model that is currently performing well in various AI fields such as natural language processing, voice recognition, and image recognition. We propose a multimodal-based improved transformer model that is improved to increase the accuracy of recommendation by using dialogue (text) and fashion (image) information together for data preprocessing and data representation. We also propose a method to improve accuracy through data improvement by analyzing the data. The proposed system has a recommendation accuracy score of 0.6563 WKT (Weighted Kendall's tau), which significantly improved the existing system's 0.3372 WKT by 0.3191 WKT or more.

• Journal of Smart Tourism
• /
• v.3 no.1
• /
• pp.41-47
• /
• 2023

Tourism and hospitality have encountered significant changes in recent years as a result of the rapid development of information technology (IT). Customers now expect more expedient services and customized travel experiences, which has intensified competition among service providers. To meet these demands, businesses have adopted sophisticated IT applications such as ChatGPT, which enables real-time interaction with consumers and provides recommendations based on their preferences. This paper focuses on the AI support-prompt middleware system, which functions as a mediator between generative AI and human users, and discusses two operational rules associated with it. The first rule is the Information Processing Rule, which requires the middleware system to determine appropriate responses based on the context of the conversation using techniques for natural language processing. The second rule is the Information Presentation Rule, which requires the middleware system to choose an appropriate language style and conversational attitude based on the gravity of the topic or the conversational context. These rules are essential for guaranteeing that the middleware system can fathom user intent and respond appropriately in various conversational contexts. This study contributes to the planning and analysis of service design by deriving design rules for middleware systems to incorporate artificial intelligence into tourism services. By comprehending the operation of AI support-prompt middleware systems, service providers can design more effective and efficient AI-driven tourism services, thereby improving the customer experience and obtaining a market advantage.