• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1396-1412
• /
• 2023

Conversation modeling is an important and challenging task in the field of natural language processing because it is a key component promoting the development of automated humanmachine conversation. Most recent research concerning conversation modeling focuses only on the current utterance (considered as the current question) to generate a response, and thus fails to capture the conversation's logic from its beginning. Some studies concatenate the current question with previous conversation sentences and use it as input for response generation. Another approach is to use an encoder to store all previous utterances. Each time a new question is encountered, the encoder is updated and used to generate the response. Our approach in this paper differs from previous studies in that we explicitly separate the encoding of the question from the encoding of its context. This results in different encoding models for the question and the context, capturing the specificity of each. In this way, we have access to the entire context when generating the response. To this end, we propose a deep neural network-based model, called the Context Model, to encode previous utterances' information and combine it with the current question. This approach satisfies the need for context information while keeping the different roles of the current question and its context separate while generating a response. We investigate two approaches for representing the context: Long short-term memory and Convolutional neural network. Experiments show that our Context Model outperforms a baseline model on both ConvAI2 Dataset and a collected dataset of conversational English.

• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1252-1261
• /
• 2009

One notable challenge in video searching and summarizing is extracting semantic from video contents and annotating context for video contents. Video semantic or context could be obtained by two methods to extract objects and contexts between objects from video. However, the method that use just to extracts objects do not express enough semantic for shot or scene as it does not describe relation and interaction between objects. To be more effective, after extracting some objects, context like relation and interaction between objects needs to be extracted from conversation situation. This paper is a study for how to detect speaker and how to compose context for talking to annotate conversation context. For this, based on this study, we proposed the methods that characters are recognized through face recognition technology, speaker is detected through mouth motion, conversation context is extracted using the rule that is composed of speaker existing, the number of characters and subtitles existing and, finally, scene context is changed to xml file and saved.

• Korean Journal of Child Studies
• /
• v.31 no.5
• /
• pp.63-77
• /
• 2010

This study was to investigate the differences of 'math talks' between concept-based storybook reading and context-based storybook reading activities. The teachers carried out storybook reading activities with their children using either four concept-based storybooks or four context-based storybooks. Fifty-six storybook reading activities from seven kindergarten classrooms were observed. The data were collected through participant observations and audio recordings. The transcriptions of 'math talks' during storybook reading activity were classified in terms of the levels of instructional conversation, types of mathematizing, and the mathematical processes involved. The results indicated that the 'math talks' during the concept-based storybook reading activity were higher than those of the context-based storybook reading activity in terms of both the instructional conversation and in quantifying and redescribing of mathematizing. However, the 'math talks' during the context-based storybook reading activity were higher than those of the concept-based storybook reading activity in connecting and reasoning of the mathematical processes involved. These findings suggest that early childhood teachers need to improve the level of instructional conversation during math storybook reading activities.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.551-563
• /
• 2022

This study aims to identify the effect on the user experiences when the embodied agent in a self-driving car interacts with emotional expressions by using 'interjection'. An experimental study was designed with two conditions: the inclusion of injections in the agent's conversation feedbacks (with interjections vs. without interjections) and the type of conversation (task-oriented conversation vs. social-oriented conversation). The online experiment was conducted with the four video clips of conversation scenario treatments and measured intimacy, likability, trust, social presence, perceived anthropomorphism, and future intention to use. The result showed that when the agent used interjection, the main effect on social presence was found in both conversation types. When the agent did not use interjection in the task-oriented conversation, trust and future intention to use were higher than when the agent talked with emotional expressions. In the context of the conversation with the AI agent in a self-driving car, we found only the effect of adding emotional expression by using interjection on the enhancing social presence, but no effect on the other user experience factors.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.137-150
• /
• 2004

This paper investigates the prosodic characteristics of discourse boundaries in spontaneous conversation. In this study, the term 'conversation' is taken to refer to a kind of talk in which two or more participants alternate in speaking about particular topics. Such a definition implies that there are at least two sorts of structures in the conversation: textual structure and interactive structure. This requires us to consider not just the textual influences on prosody but also the impact of interactive context. The aim of this study is to find out the acoustic-prosodic means used by speakers to signal discourse boundaries in conversational interaction. The results show that the conflict between the structural level and the interactive level obliges the speakers to reorganize the prosodic variables according to the type of discourse boundaries.

• 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.2
• /
• pp.179-184
• /
• 2021

In this study, the conversation behavior of users is investigated by using in-vehicle voice interaction system. The purpose of this study is to identify the elements of conversations that the users expect in voice interactions with systems and present the structural improvements to enable the voice interactions similar to those between people. To observe the users' behavior of voice interaction in the vehicle, the data through contextual inquiry are collected and the interview contents are analyzed by using the open coding. We have been able to explore the usefulness of voice interaction features, which are of great importance in that they increase the user's satisfaction with the features and their usage persistence. This study is meaningful in analyzing the user's empirical needs for the technology of interpersonal model from the perspective of conversation.

• Journal of Convergence for Information Technology
• /
• v.7 no.6
• /
• pp.245-251
• /
• 2017

This presents an English conversation training system with which learners train their conversation skills in English, which makes them converse with native speaker characters in a virtual reality environment with voice. The proposed system allows the learners to talk with multiple native speaker characters in varous scenarios in the virtual reality environment. It recongizes voices spoken by the learners and generates voices by a speech synthesis method. The interaction with characters in the virtual reality environment in voice makes the learners immerged in the conversation situations. The scoring system which evaluates the learner's pronunciation provides the positive feedback for the learners to get engaged in the learning context.

• The Mathematical Education
• /
• v.41 no.3
• /
• pp.329-339
• /
• 2002

This study analyzes the epistemological meaning of‘social construction’in mathematical instruction. The perspective that consider the cognition of mathematical concept as a social construction is explained by a cyclic scheme of an academic context and a school context. Both of the contexts require a public procedure, social conversation. However, there is a considerable difference that in the academic context it is Lakatos' ‘logic of mathematical discovery’In the school context, it is Vygotsky's‘instructional and learning interaction’. In the situation of mathematics education, the‘society’which has an influence on learner's cognition does not only mean‘collective members’, but‘form of life’which is constituted by the activity with purposes, language, discourse, etc. Teachers have to play a central role that guide and coordinate the educational process involving interactions with learners in this context. We can get useful suggestions to mathematics education through this consideration of the social contexts and levels to form didactical situations of mathematics.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.37-45
• /
• 2003

This study attempted to determine the effects of a context-based drawing task on the language expression of a severe Wernicke's and Broca's aphasic. The subjects in this study showed a poor auditory comprehension and naming performance. They also showed paraphasia and perseveration. This study focused on improving language expression by a drawing task based on conversation at hand. Ten target words were chosen which were easily drawnable and familiar to the subjects. The results showed that the context-based drawing task was effective on improving the subjects' confrontation naming ability and expressive language ability in terms of explanation of sentences. In addition, the Broca's aphasic showed improved naming ability when the contextual cues were given and he was supposed to spontaneously name words.