• Journal of Families and Better Life
• /
• v.22 no.6 s.72
• /
• pp.219-232
• /
• 2004

The purpose of this study was to investigate the gender differences in conversational styles of students. This research based on Quantitative survey and qualitative observation. The quantitative data were collected by questionnaire from 708 respondents who were college students and resided in Sunchon. Statistical methods for the data analysis were frequencies, t-test. The cases of observation were 21. As a result, gender differences were founded in lots of conversational styles. Women showed more tendencies than men In communi-cations to listen, to make relationships, to take care of others, to express intimacy and to make private conversation. Men tended to dominate others, to show off capacities and to make public conversation. This gender differences in conversational styles were related to sex role and major studies. From this results it was proposed that education on gender differences in conversational styles should be developed for students to improve their communication skills and to adapt their changing sex role.

• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.377-387
• /
• 2004

This paper describes a tree-based conversational interface supporting efficient presentation of turn relations on online conversation. Most of conventional conversational interfaces are difficult to make use of formal conversation such as group meeting, decision-making, etc. due to very simplicity of a con versational interface and restriction of data structure of conversational messages. And a tree-based conversational interface supports formal conversation, but they are difficult to present turn relations because of jumpy display by locations of replied turns and distance between replied turns, etc. So this paper suggests a tree-based conversational interface to present efficiently turn relations using XML-based messages with merits of a text-based interface. The suggested conversational interface was implemented by using XML-, DOM, and JDK. And this paper showed that the conversational interface could be applied to conversation system using client- server architecture. Applications for the conversational interface are as follows: collaboration, distance teaming, online game, etc.

• English Language & Literature Teaching
• /
• v.12 no.1
• /
• pp.77-101
• /
• 2006

The present study examines various pedagogical functions of conversational repair strategies employed by the teacher in the ESL classroom. As part of interactional resources, conversational repair is defined as the treatment of trouble occurring in interactive language use and is originally designed to deal with communication problems. Research on conversational repair has focused on ordinary conversation and organization of repair practices. Studies on more pedagogical functions of repair sequences initiated by the teacher are very few. The data were from five hours of ESL structure classes in an intensive English institute at a large U.S. university. They were closely transcribed and microanalyzed following the conversation-analytic methodology. The analysis found that ESL teachers' repair techniques not only resolve communication problems but they are also designed to serve several important instructional purposes of teaching the target language. They include creating opportunities of comprehensible input, inducing modified comprehensible output from students, guiding and controlling student output, and initiating corrections by initiating repair.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.77-87
• /
• 2024

With the recent advancements in artificial intelligence, various chatbots have emerged, efficiently performing everyday tasks such as hotel bookings, news updates, and legal consultations. Particularly, generative chatbots like ChatGPT are expanding their applicability by generating original content in fields such as education, research, and the arts. However, the training of these AI chatbots requires large volumes of conversational text data, such as customer service records, which has led to privacy infringement cases domestically and internationally due to the use of unrefined data. This study proposes a methodology to quantitatively assess the re-identification risk of personal information contained in conversational text data used for training AI chatbots. To validate the proposed methodology, we conducted a case study using synthetic conversational data and carried out a survey with 220 external experts, confirming the significance of the proposed approach.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.27-38
• /
• 2023

In this paper, we propose a conversational AI agent based on continual learning that can continuously learn and grow with new data over time. A continual learning-based conversational AI agent consists of three main components: Task manager, User attribute extraction, and Auto-growing knowledge graph. When a task manager finds new data during a conversation with a user, it creates a new task with previously learned knowledge. The user attribute extraction model extracts the user's characteristics from the new task, and the auto-growing knowledge graph continuously learns the new external knowledge. Unlike the existing conversational AI agents that learned based on a limited dataset, our proposed method enables conversations based on continuous user attribute learning and knowledge learning. A conversational AI agent with continual learning technology can respond personally as conversations with users accumulate. And it can respond to new knowledge continuously. This paper validate the possibility of our proposed method through experiments on performance changes in dialogue generation models over time.

• 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.

• Phonetics and Speech Sciences
• /
• v.3 no.3
• /
• pp.19-26
• /
• 2011

Previous laboratory studies have shown that prosodic structures are encoded in the modulations of phonetic patterns of speech including suprasegmental as well as segmental features. Drawing on a prosodically annotated large-scale speech data from the Buckeye corpus of conversational speech of American English, the current study first evaluated the reliability of prosody annotation by a large number of ordinary listeners and later examined whether and how prosodic prominence influences the phonetic realization of multiple acoustic parameters in everyday conversational speech. The results showed that all the measures of acoustic parameters including pitch, loudness, duration, and spectral balance are increased when heard as prominent. These findings suggest that prosodic prominence enhances the phonetic characteristics of the acoustic parameters. The results also showed that the degree of phonetic enhancement vary depending on the types of the acoustic parameters. With respect to the formant structure, the findings from the present study more consistently support Sonority Expansion Hypothesis than Hyperarticulation Hypothesis, showing that the lexically stressed vowels are hyperarticulated only when hyperarticulation does not interfere with sonority expansion. Taken all into account, the present study showed that prosodic prominence modulates the phonetic realization of the acoustic parameters to the direction of the phonetic strengthening in everyday conversational speech and ordinary listeners are attentive to such phonetic variation associated with prosody in speech perception. However, the present study also showed that in everyday conversational speech there is no single dominant acoustic measure signaling prosodic prominence and listeners must attend to such small acoustic variation or integrate acoustic information from multiple acoustic parameters in prosody perception.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.77-85
• /
• 2023

After COVID-19, communication through online platforms has increased, leading to an accumulation of massive amounts of conversational text data. With the growing importance of summarizing this text data to extract meaningful information, there has been active research on deep learning-based abstractive summarization. However, conversational data, compared to structured texts like news articles, often contains missing or transformed information, necessitating consideration from multiple perspectives due to its unique characteristics. In particular, vocabulary omissions and unrelated expressions in the conversation can hinder effective summarization. Therefore, in this study, we restructured by considering the characteristics of Korean conversational data, fine-tuning a pre-trained text summarization model based on KoBART, and improved conversation data summary perfomance through a refining operation to remove redundant elements from the summary. By restructuring the sentences based on the order of utterances and extracting a central speaker, we combined methods to restructure the conversation around them. As a result, there was about a 4 point improvement in the Rouge-1 score. This study has demonstrated the significance of our conversation restructuring approach, which considers the characteristics of dialogue, in enhancing Korean conversation summarization performance.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.81-90
• /
• 2020

This paper describes a method of building Korean conversational speech data in the emergency medical domain and proposes an annotation method for the collected data in order to improve speech recognition performance. To suggest future research directions, baseline speech recognition experiments were conducted by using partial data that were collected and annotated. All voices were recorded at 16-bit resolution at 16 kHz sampling rate. A total of 166 conversations were collected, amounting to 8 hours and 35 minutes. Various information was manually transcribed such as orthography, pronunciation, dialect, noise, and medical information using Praat. Baseline speech recognition experiments were used to depict problems related to speech recognition in the emergency medical domain. The Korean conversational speech data presented in this paper are first-stage data in the emergency medical domain and are expected to be used as training data for developing conversational systems for emergency medical applications.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.178-183
• /
• 2008

The goal of this study is finding flow-map in conversation what is going on user and embodied conversational agent by analysing that conversation. Specifically, this study not only find elements of conversation, but also draw out patterns of conversation can be exist for dialogue ability between user and Embodied conversational agent. To do this, we collect data through in-depth one to one interview, and then we analysis collected data to try to find out element of user-agent conversation based on qualitative research refer to the theory of conversation analytics and type of conversation. As a result, six flow map is deducted Especially, the irregular conversation is hard to find in human-human conversation, and the frequency is the most in data. In addition, when elements of interruption came out, be hostile to partner or correct the press conversation. This study can have positive effect to embodied conversation agent developer, user and service offerer because this study find the type of conversation through analysis that between embodied conversational agent and user.