Topic
Chatbot
About: Chatbot is a research topic. Over the lifetime, 2415 publications have been published within this topic receiving 24372 citations. The topic is also known as: IM bot & AI chatbot.
Papers published on a yearly basis
Papers
More filters
•
TL;DR: This system adapts TransferTransfo (Wolf et al., 2019) learning approach that fine-tunes a large-scale pre-trained language model with multi-task objectives: response language modeling, response prediction and dialogue emotion detection.
Abstract: In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach that fine-tunes a large-scale pre-trained language model with multi-task objectives: response language modeling, response prediction and dialogue emotion detection. We evaluate our model on the recently proposed empathetic-dialogues dataset (Rashkin et al., 2019), the experiment results show that CAiRE achieves state-of-the-art performance on dialogue emotion detection and empathetic response generation.
20 citations
••
TL;DR: The key novelty of the proposed approach is the automated machine-machine conversational knowledge sharing and reuse, which is an important step towards building the new conversational agents skipping the difficult and time-consuming procedure of knowledge acquisition.
Abstract: Acquiring knowledge for conversation modeling is an important task in the process of building a Conversational Agent (Chatbot). However, it is a quite difficult process that requires too much time and efforts. To overcome these difficulties, in this paper, we demonstrate a novel methodology for the automatic conversational knowledge extraction from an existing Chatbot. Extracted knowledge will be used as training dataset for building a Neural Network Conversational Agent. The experiments in the paper show that our proposed approach can be used for the automatic knowledge extraction from any type of Chatbot on the Internet. The experiment that is presented in this paper has two phases. In the first phase, we present a methodology for the conversational knowledge extraction. In the second phase of the experiment, we introduce a methodology for building a new Neural Conversational Agent using a deep learning Neural Network framework. The key novelty of our proposed approach is the automated machine-machine conversational knowledge sharing and reuse. This is an important step towards building the new conversational agents skipping the difficult and time-consuming procedure of knowledge acquisition.
20 citations
••
TL;DR: In this article, a mental health and wellbeing chatbot for secondary school and health care settings was developed with youth, technology partners and expert stakeholders, which is created to communicate evidence based resources, wellbeing support, educational mental health information and adaptive coping strategies.
Abstract: There are many young people who experience mental health and wellbeing challenges. A potential negative mental health trigger for some youth is a struggle to cope with stress at school, feelings of depression and anxiety and availability of adequate help for these stressors. In response to youth needs a mental health and wellbeing Chatbot has been co-developed with youth, technology partners and expert stakeholders. An element of the Chatbot is powered by artificial intelligence and rules based AI using natural language processing. It is created to communicate evidence based resources, wellbeing support, educational mental health information and adaptive coping strategies. This paper will discuss how the Chatbot has been developed, highlighting its participatory, co-design process with youth who are the key stakeholders to benefit from this digital tool. Research from interviews and surveys informed the creation of the Chabots personality and its character design. Examples of the conversation design and content development are provided. The paper finishes with how, if at all, digital tools such as Chatbot applications could support the mental health of young people in secondary schools or health care settings in conjunction with the wellbeing or health care team, concluding with lessons learned and cautions.
20 citations
••
TL;DR: One-Match and All-Match Categories for keywords matching in chatbot is shown to be an improvement over previous techniques in the context of keywords arrangement for matching precedence and keywords variety for matching flexibility.
Abstract: Problem statement: Artificial intelligence chatbot is a technology that makes interactions between men and machines using natural language possible. From literature of chatbot’s keywords/pattern matching techniques, potential issues for improvement had been discovered. The discovered issues are in the context of keywords arrangement for matching precedence and keywords variety for matching flexibility. Approach: Combining previous techniques/mechanisms with some additional adjustment, new technique to be used for keywords matching process is proposed. Using newly developed chatbot named ViDi (abbreviation for Virtual Diabetes physician which is a chatbot for diabetes education activity) as a testing medium, the proposed technique named One-Match and All-Match Categories (OMAMC) is being used to test the creation of possible keywords surrounding one sample input sentence. The result for possible keywords created by this technique then being compared to possible keywords created by previous chatbot’s techniques surrounding the same sample sentence in matching precedence and matching flexibility context. Results: OMAMC technique is found to be improving previous matching techniques in matching precedence and flexibility context. This improvement is seen to be useful for shortening matching time and widening matching flexibility within the chatbot’s keywords matching process. Conclusion: OMAMC for keywords matching in chatbot is shown to be an improvement over previous techniques in the context of keywords arrangement for matching precedence and keywords variety for matching flexibility.
20 citations
••
TL;DR: In this paper , an experimental use case of an educational AI chatbot called AsasaraBot, designed to teach high school students cultural content in a foreign language, i.e., English or French, was presented.
Abstract: Using advanced artificial intelligence (AI) technology in learning environments is one of the latest challenges for educators and education policymakers. Conversational AI brings new possibilities for alternative and innovative Information and Communication Technologies (ICT) tools, such as ΑΙ chatbots. This paper reports on field experiments with an AI chatbot and provides insights into its contribution to Content and Language Integrated Learning (CLIL). More specifically, this paper presents an experimental use case of an educational AI chatbot called AsasaraBot, designed to teach high school students cultural content in a foreign language, i.e., English or French. The content is related to the Minoan Civilization, emphasizing the characteristic figurine of the Minoan Snake Goddess. The related chatbot-based educational program has been evaluated at public and private language schools in Greece. The findings from these experiments show that the use of AI chatbot technology for interactive ICT-based learning is suitable for learning foreign languages and cultural content at the same time. The AsasaraBot AI chatbot has been designed and implemented in the context of a postgraduate project using open-source and free software.
20 citations