How to Keep an Online Learning Chatbot From Being Corrupted

Chai, Yixuan; Li, Guohua; Jin, Ziwei; Sun, Deqing

doi:10.1109/ijcnn48605.2020.9206897

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One-shot learning, on the other hand, focuses on learning from a single example [126]. This method is especially beneficial for personalizing interactions or quickly incorporating user-specific preferences and contexts into the chatbot's response framework.…”

Section: Few-shot Zero-shot and One-shot Learningmentioning

confidence: 99%

Error Correction and Adaptation in Conversational AI: A Review of Techniques and Applications in Chatbots

Izadi,

Forouzanfar

2024

View full text Add to dashboard Cite

This study explores the progress of chatbot technology, focusing on the aspect of error correction to enhance these smart conversational tools. Chatbots, powered by artificial intelligence (AI), are increasingly prevalent across industries such as customer service, healthcare, e-commerce, and education. Despite their use and increasing complexity, chatbots are prone to errors like misunderstandings, inappropriate responses, and factual inaccuracies. These issues can have an impact on user satisfaction and trust. This research provides an overview of chatbots, conducts an analysis of errors they encounter, and examines different approaches to rectifying these errors. These approaches include using data-driven feedback loops, involving humans in the learning process, and adjusting through learning methods like reinforcement learning, supervised learning, unsupervised learning, semi-supervised learning, and meta-learning. Through real life examples and case studies in different fields, we explore how these strategies are implemented. Looking ahead, we explore the different challenges faced by AI-powered chatbots, including ethical considerations and biases during implementation. Furthermore, we explore the transformative potential of new technological advancements, such as explainable AI models, autonomous content generation algorithms (e.g., generative adversarial networks), and quantum computing to enhance chatbot training. Our research provides information for developers and researchers looking to improve chatbot capabilities, which can be applied in service and support industries to effectively address user requirements.

show abstract

Section: Few-shot Zero-shot and One-shot Learningmentioning

confidence: 99%

Error Correction and Adaptation in Conversational AI: A Review of Techniques and Applications in Chatbots

Izadi,

Forouzanfar

2024

View full text Add to dashboard Cite

show abstract

“…The sentences are categorized into four classes: normal sentences, insulting sentences, negative sentences about a different person, or sentences that may indicate a dangerous situation. Chai et al [241] developed an offensive-response dataset, which consists of 110K input-response chat records in which the response is either appropriate or offensive. These databases can assist in training CAs, allowing the CAs to identify different sensitive situations to respond accordingly.…”

Section: Datasets For Social Assistancementioning

confidence: 99%

Conversational Agents: Goals, Technologies, Vision and Challenges

Allouch

Azaria

Azoulay

2021

Sensors

View full text Add to dashboard Cite

In recent years, conversational agents (CAs) have become ubiquitous and are a presence in our daily routines. It seems that the technology has finally ripened to advance the use of CAs in various domains, including commercial, healthcare, educational, political, industrial, and personal domains. In this study, the main areas in which CAs are successful are described along with the main technologies that enable the creation of CAs. Capable of conducting ongoing communication with humans, CAs are encountered in natural-language processing, deep learning, and technologies that integrate emotional aspects. The technologies used for the evaluation of CAs and publicly available datasets are outlined. In addition, several areas for future research are identified to address moral and security issues, given the current state of CA-related technological developments. The uniqueness of our review is that an overview of the concepts and building blocks of CAs is provided, and CAs are categorized according to their abilities and main application domains. In addition, the primary tools and datasets that may be useful for the development and evaluation of CAs of different categories are described. Finally, some thoughts and directions for future research are provided, and domains that may benefit from conversational agents are introduced.

show abstract

“…With the widespread application of AI products, the abuse of AI technology without human values consideration has drawn wide concern in the last decade. Negative examples such as offensive remarks by conversational assistants [77] and DeepFake fraud cause losses to society and even harm the development of the AI industry and research. To alleviate this concern and build AI trustworthiness, it is necessary to incorporate alignment with human values over the whole lifecycle of an AI system, which requires efforts on not only product design but also AI technology development.…”

Section: Value Alignmentmentioning

confidence: 99%

Trustworthy AI: From Principles to Practices

Li¹,

Pan²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fast developing artificial intelligence (AI) technology has enabled various applied systems deployed in the real world, impacting people's everyday lives. However, many current AI systems were found vulnerable to imperceptible attacks, biased against underrepresented groups, lacking in user privacy protection, etc., which not only degrades user experience but erodes the society's trust in all AI systems. In this review, we strive to provide AI practitioners a comprehensive guide towards building trustworthy AI systems. We first introduce the theoretical framework of important aspects of AI trustworthiness, including robustness, generalization, explainability, transparency, reproducibility, fairness, privacy preservation, alignment with human values, and accountability. We then survey leading approaches in these aspects in the industry. To unify the current fragmented approaches towards trustworthy AI, we propose a systematic approach that considers the entire lifecycle of AI systems, ranging from data acquisition to model development, to development and deployment, finally to continuous monitoring and governance. In this framework, we offer concrete action items to practitioners and societal stakeholders (e.g., researchers and regulators) to improve AI trustworthiness. Finally, we identify key opportunities and challenges in the future development of trustworthy AI systems, where we identify the need for paradigm shift towards comprehensive trustworthy AI systems.

show abstract

How to Keep an Online Learning Chatbot From Being Corrupted

Cited by 5 publications

References 17 publications

Error Correction and Adaptation in Conversational AI: A Review of Techniques and Applications in Chatbots

Error Correction and Adaptation in Conversational AI: A Review of Techniques and Applications in Chatbots

Conversational Agents: Goals, Technologies, Vision and Challenges

Trustworthy AI: From Principles to Practices

Contact Info

Product

Resources

About