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.

Conversational Repair in Chatbots for Customer Service: The Effect of Expressing Uncertainty and Suggesting Alternatives.

Abstract: Due to the complexity of natural language, chatbots are prone to misinterpreting user requests. Such misinterpretations may lead the chatbot to provide answers that are not adequate responses to user request – so called false positives – potentially leading to conversational breakdown. A promising repair strategy in such cases is for the chatbot to express uncertainty and suggest likely alternatives in cases where prediction confidence falls below threshold. However, little is known about how such repair affects chatbot dialogues. We present findings from a study where a solution for expressing uncertainty and suggesting likely alternatives was implemented in a live chatbot for customer service. Chatbot dialogues (N = 700) were sampled at two points in time – immediately before and after implementation – and compared by conversational quality. Preliminary analyses suggest that introducing such a solution for conversational repair may substantially reduce the proportion of false positives in chatbot dialogues. At the same time, expressing uncertainty and suggesting likely alternatives does not seem to strongly affect the dialogue process and the likelihood of reaching a successful outcome. Based on the findings, we discuss theoretical and practical implications and suggest directions for future research.

Intelligent Chatbot for Lab Security and Automation

Abstract: Artificial intelligence based communicative artefacts are called chatbots. The purpose of a chatterbot or chatbot is to render an interaction between a human and a robot in the form of speech or text. They offer the best services in a variety of areas, such as education, healthcare, transportation, etc. As per the research, nearly 85 % of product offerings will be automated by 2020. The proposed system is a voice-based chatbot that helps to improve the security and automation of a lab. The system makes use of Automatic Speaker Recognition (ASR) algorithm in order to recognize a person and allow him/her inside the lab. This allows only authorized person to access the lab facilities. The same algorithm is used for generating the list of available components in the lab based on the person's keyword input thus automating the lab components dispatch.

A Banking Chatbot Security Control Procedure for Protecting User Data Security and Privacy

Abstract: The rise of AI has prompted the financial business to enter the intelligent financial technology (FinTech). Chatbot with AI technologies is an important member of FinTech. The financial industry is actively introducing chatbot to enhance the market competitive advantage. Many banks and card issuers in the United States have introduced or developed chatbots from 2017 to increase user convenience and assist business promotion of financial institutions. However, chatbot with AI features may infringe customer security and personal privacy. Security has become an important issue that Chatbot must pay attention to. In order to improve the security of chatbot, this paper analyzes the security strategies of e-commerce (EC), and combines the AI security principles to plan the Chatbot Security Control Procedure (CSCP). CSCP uses security specifications confirmation, specifications implementation, inspection activity and improvement manners four stages to monitor chatbot. Banking chatbot with CSPS can hold advantages of chatbots, reduce the security risk, and concretely protect customer data security and personal privacy.

A Modular Architecture for Adaptive ChatBots

Abstract: We illustrate an architecture for a conversational agent based on a modular knowledge representation. This solution provides intelligent conversational agents with a dynamic and flexible behavior. The modularity of the architecture allows a concurrent and synergic use of different techniques, making it possible to use the most adequate methodology for the management of a specific characteristic of the domain, of the dialogue, or of the user behavior. We show the implementation of a proof-of-concept prototype: a set of modules exploiting different knowledge representation techniques and capable to differently manage conversation features has been developed. Each module is automatically triggered through a component, named corpus callosum, whose task is to choose, time by time, the most adequate chatbot knowledge section to activate.

Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce

Abstract: Building multi-turn information-seeking conversation systems is an important and challenging research topic. Although several advanced neural text matching models have been proposed for this task, they are generally not efficient for industrial applications. Furthermore, they rely on a large amount of labeled data, which may not be available in real-world applications. To alleviate these problems, we study transfer learning for multi-turn information seeking conversations in this paper. We first propose an efficient and effective multi-turn conversation model based on convolutional neural networks. After that, we extend our model to adapt the knowledge learned from a resource-rich domain to enhance the performance. Finally, we deployed our model in an industrial chatbot called AliMe Assist (this https URL) and observed a significant improvement over the existing online model.