Dialogue Management Research Articles

ICORPP: Interleaved commonsense reasoning and probabilistic planning on robots

Robot sequential decision-making in the real world is a challenge because it requires the robots to simultaneously reason about the current world state and dynamics, while planning actions to accomplish complex tasks. On the one hand, declarative languages and reasoning algorithms support representing and reasoning with commonsense knowledge. But these algorithms are not good at planning actions toward maximizing cumulative reward over a long, unspecified horizon. On the other hand, probabilistic planning frameworks, such as Markov decision processes (MDPs) and partially observable MDPs (POMDPs), support planning to achieve long-term goals under uncertainty. But they are ill-equipped to represent or reason about knowledge that is not directly related to actions. In this article, we present an algorithm, called iCORPP, to simultaneously estimate the current world state, reason about world dynamics, and construct task-oriented controllers. In this process, robot decision-making problems are decomposed into two interdependent (smaller) subproblems that focus on reasoning to “understand the world” and planning to “achieve the goal” respectively. The developed algorithm has been implemented and evaluated both in simulation and on real robots using everyday service tasks, such as indoor navigation, and dialog management. Results show significant improvements in scalability, efficiency, and adaptiveness, compared to competitive baselines including handcrafted action policies.

Design Knowledge for Virtual Learning Companions from a Value-centered Perspective

The increasing popularity of conversational agents such as ChatGPT has sparked interest in their potential use in educational contexts but undermines the role of companionship in learning with these tools. Our study targets the design of virtual learning companions (VLCs), focusing on bonding relationships for collaborative learning while facilitating students’ time management and motivation. We draw upon design science research (DSR) to derive prescriptive design knowledge for VLCs as the core of our contribution. Through three DSR cycles, we conducted interviews with working students and experts, held interdisciplinary workshops with the target group, designed and evaluated two conceptual prototypes, and fully coded a VLC instantiation, which we tested with students in class. Our approach has yielded 9 design principles, 28 meta-requirements, and 33 design features centered around the value-in-interaction. These encompass Human-likeness and Dialogue Management, Proactive and Reactive Behavior, and Relationship Building on the Relationship Layer (DP1,3,4), Adaptation (DP2) on the Matching Layer, as well as Provision of Supportive Content, Fostering Learning Competencies, Motivational Environment, and Ethical Responsibility (DP5-8) on the Service Layer.

Unraveling the thread: understanding and addressing sequential failures in human-robot interaction.

Interaction is a dynamic process that evolves in real time. Participants interpret and orient themselves towards turns of speech based on expectations of relevance and social/conversational norms (that have been extensively studied in the field of Conversation analysis). A true challenge to Human Robot Interaction (HRI) is to develop a system capable of understanding and adapting to the changing context, where the meaning of a turn is construed based on the turns that have come before. In this work, we identify issues arising from the inadequate handling of the sequential flow within a corpus of in-the-wild HRIs in an open-world university library setting. The insights gained from this analysis can be used to guide the design of better systems capable of handling complex situations. We finish by surveying efforts to mitigate the identified problems from a natural language processing/machine dialogue management perspective.

Coupling Sentiment and Arousal Analysis Towards an Affective Dialogue Manager

Coupling Sentiment and Arousal Analysis Towards an Affective Dialogue Manager

Design and Implementation of Chatbot using Python

Chatbots have become increasingly popular in recent years, with applications spanning customer support, virtual assistants, and more. This research paper explores the design and implementation of a chatbot using Python. We delve into various aspects of chatbot development, including natural language processing (NLP), dialogue management, and user interface integration. The paper discusses key Python libraries and tools for building a chatbot and presents a case study demonstrating the creation of a simple chatbot.

Health Care Chatbot

Artificial intelligence (AI) is at the forefront of transforming numerous aspects of our lives by modifying the way we analyze information and improving decision-making through problem solving, reasoning, and learning. Machine learning (ML) is a subset of AI that improves its performance based on the data provided to a generic algorithm from experience rather than defining rules in traditional approaches. Advancements in ML have provided benefits in terms of accuracy, decision-making, quick processing, cost-effectiveness, and handling of complex data. Chatbots, also known as chatter robots, smart bots, conversational agents, digital assistants, or intellectual agents, are prime examples of AI systems that have evolved from ML. This paper presents Healthcare Chatbot using Artificial Intelligence that can make a human-system interaction to resolve basic queries regarding health parameters before consulting a doctor. The actual purpose behind this work is to work on the user's symptoms and to provide medical suggestions according to it, to reduce the time and cost required for the process. The chatbot works on provided input by the user, It takes sentence keywords and makes decisions to solve the user's query and answers it accordingly. Given these effectual benefits, it is not surprising that chatbots have rapidly evolved over the past 2 decades and integrated themselves into numerous fields, such as entertainment, travel, gaming, robotics, and security. Chatbots have been proven to be particularly applicable in various health care components that usually involve face-to-face interactions. With their ability for complex dialog management and conversational flexibility, integration of chatbot technology into clinical practice may reduce costs, refine workflow efficiencies, and improve patient outcomes. A user can be able to recognize the actual disease by providing symptoms of it. As if a person will also know about the solutions or we can say precautions and remedies that they should take accordingly.

"I don't know how to help with that" - Learning from Limitations of Modern Conversational Agent Systems in Caregiving Networks

While commercial conversational agents (CA) (i.e. Google assistant, Siri, Alexa) are widely used, these systems have limitations in error-handling, flexibility, personalization and overall dialogue management that are amplified in care coordination settings. In this paper, we synthesize and articulate these limitations through quantitative and qualitative analysis of 56 older adults interacting with a commercial CA deployed in their home for a 10 week period. We look at the CA as a compensatory technology in an older adult's care network. We argue that the CA limitations are rooted in the rigid cue-and-response style of task-oriented interactions common in CAs. We then propose a redesign for CA conversation flow to favor flexibility and personalization that is nonetheless viable within the limitations of current AI and machine learning technologies. We explore design tradeoffs to better support the usability needs of older adults compared to current design optimizations driven by efficiency and privacy goals.

Intelligent Educational Recommendation Platform with AI Chatbots

The objectives of this research were as follows. 1) Analyze the intelligent educational recommendation platform with AI Chatbots. 2) Design the architecture of the intelligent educational recommendation platform with AI Chatbots. 3) Develop the architecture of the intelligent educational recommendation platform with AI Chatbots. 4) Study the appropriateness of developing the intelligent educational recommendation platform with AI Chatbots. The sample used in the research was seven experts in information system development from various institutions in higher education. The architecture of the intelligent educational recommendation platform with AI Chatbots there is two main components: 1) Stakeholders consisting of system administrators and external users, and 2) The working process of the intelligent educational recommendation platform with AI Chatbots consists of four parts including natural language processing, dialog management, database and application programming interface (API), and response generation. Assessment of the appropriateness of the architecture of the intelligent educational recommendation platform with AI Chatbots found that 1) the architecture of the intelligent educational recommendation platform with AI Chatbots, overall at a high appropriated, 2) the architecture of the intelligent educational recommendation platform with AI Chatbots, an individual element at a high appropriated, and 3) the architecture of the intelligent educational recommendation platform with AI Chatbots, Integrated elements at a high appropriated. As described earlier, the architecture of the intelligent educational recommendation platform with AI Chatbots can be a guideline for developing with AI Chatbots in the future.

Seeing eye to eye: trustworthy embodiment for task-based conversational agents.

Smart speakers and conversational agents have been accepted into our homes for a number of tasks such as playing music, interfacing with the internet of things, and more recently, general chit-chat. However, they have been less readily accepted in our workplaces. This may be due to data privacy and security concerns that exist with commercially available smart speakers. However, one of the reasons for this may be that a smart speaker is simply too abstract and does not portray the social cues associated with a trustworthy work colleague. Here, we present an in-depth mixed method study, in which we investigate this question of embodiment in a serious task-based work scenario of a first responder team. We explore the concepts of trust, engagement, cognitive load, and human performance using a humanoid head style robot, a commercially available smart speaker, and a specially developed dialogue manager. Studying the effect of embodiment on trust, being a highly subjective and multi-faceted phenomena, is clearly challenging, and our results indicate that potentially, the robot, with its anthropomorphic facial features, expressions, and eye gaze, was trusted more than the smart speaker. In addition, we found that embodying a conversational agent helped increase task engagement and performance compared to the smart speaker. This study indicates that embodiment could potentially be useful for transitioning conversational agents into the workplace, and further in situ, "in the wild" experiments with domain workers could be conducted to confirm this.

A systematic review A Conversational interface agent for the export business acceleration

Conversational agents, which understand, respond to, and learn from each interaction using Automatic Speech Recognition (ASR), Natural Language Processing (NLP), Advanced Dialog Management, and Machine Learning (ML), have become more common in recent years. Conversational agents, also referred to as chatbots, are used to have real-time conversations with individuals. As a result, conversational agents are now being used in a variety of sectors, including those in education, healthcare, marketing, customer assistance, and entertainment. Conversational agents, which are frequently used as chatbots and virtual or AI helpers, show how computational linguistics is used in everyday life. It can be challenging to pinpoint the variables that affect the use of conversational agents for business acceleration and to defend their utility in order to enhance export company. This paper provides a summary of the evolution of conversational agents from a straightforward model to a sophisticated intelligent system, as well as how they are applied in various practical contexts. This study contributes to the body of literature on information systems by contrasting the different conversational agent types based on the export business acceleration interface. This paper also identifies the challenges conversational applications experience today and makes recommendations for further research.

The Eclectic Approach in English Language Teaching Applications: A Qualitative Synthesis of the Literature

This paper proposes a study of the methodologies used to teach English as a second language through computer applications. It reviews the different methodologies used in language teaching in order to contrast them with different fundamental approaches. It examines the applications used for teaching English online, especially those in line with personalised learning environments and learner-centred autonomy. The use of a mixed methodology is reported, allowing the selection of papers from both a traditional systematic review and the search engine elicit.org. Finally, it is concluded that Blended Learning is the most appropriate method, highlighting that current applications are mainly based on the Audio-Lingual method, which limits their practical use in wider contexts. Further research is needed on software applications that prioritise personalised learning environments with learner-centred autonomy, incorporating technologies based on Blended Learning and artificial intelligence (AI). To this end, it is proposed in the future to develop an application using Automatic Speech Recognition (ASR), Text To Speech (TTS), Natural Language Understanding (NLU) and Dialog Management (DM) algorithms, focusing on the above and simulating the capabilities of a teacher. This may lead to innovations in the development of software applications capable of integrating different methods, teaching modalities and learning methods.

A Weighted Heterogeneous Graph-Based Dialog System.

Knowledge-based dialog systems have attracted increasing research interest in diverse applications. However, for disease diagnosis, the widely used knowledge graph (KG) is hard to represent the symptom-symptom and symptom-disease relations since the edges of traditional KG are unweighted. Most research on disease diagnosis dialog systems highly relies on data-driven methods and statistical features, lacking profound comprehension of symptom-symptom and symptom-disease relations. To tackle this issue, this work presents a weighted heterogeneous graph-based dialog system for disease diagnosis. Specifically, we build a weighted heterogeneous graph based on symptom co-occurrence and the proposed symptom frequency-inverse disease frequency. Then, this work proposes a graph-based deep Q -network (graph-DQN) for dialog management. By combining graph convolutional network (GCN) with DQN to learn the embeddings of diseases and symptoms from both the structural and attribute information in the weighted heterogeneous graph, graph-DQN could capture the symptom-disease relations and symptom-symptom relations better. Experimental results show that the proposed dialog system rivals the state-of-the-art models. More importantly, the proposed dialog system can complete the task with fewer dialog turns and possess a better distinguishing capability on diseases with similar symptoms.

Artificial Emotional Intelligence in Socially Assistive Robots for Older Adults: A Pilot Study.

This paper presents our recent research on integrating artificial emotional intelligence in a social robot (Ryan) and studies the robot's effectiveness in engaging older adults. Ryan is a socially assistive robot designed to provide companionship for older adults with depression and dementia through conversation. We used two versions of Ryan for our study, empathic and non-empathic. The empathic Ryan utilizes a multimodal emotion recognition algorithm and a multimodal emotion expression system. Using different input modalities for emotion, i.e. facial expression and speech sentiment, the empathic Ryan detects users emotional state and utilizes an affective dialogue manager to generate a response. On the other hand, the non-empathic Ryan lacks facial expression and uses scripted dialogues that do not factor in the users emotional state. We studied these two versions of Ryan with 10 older adults living in a senior care facility. The statistically significant improvement in the users' reported face-scale mood measurement indicates an overall positive effect from the interaction with both the empathic and non-empathic versions of Ryan. However, the number of spoken words measurement and the exit survey analysis suggest that the users perceive the empathic Ryan as more engaging and likable.

CP-Rec: Contextual Prompting for Conversational Recommender Systems

The conversational recommender system (CRS) aims to provide high-quality recommendations through interactive dialogues. However, previous CRS models have no effective mechanisms for task planning and topic elaboration, and thus they hardly maintain coherence in multi-task recommendation dialogues. Inspired by recent advances in prompt-based learning, we propose a novel contextual prompting framework for dialogue management, which optimizes prompts based on context, topics, and user profiles. Specifically, we develop a topic controller to sequentially plan the subtasks, and a prompt search module to construct context-aware prompts. We further adopt external knowledge to enrich user profiles and make knowledge-aware recommendations. Incorporating these techniques, we propose a conversational recommender system with contextual prompting, namely CP-Rec. Experimental results demonstrate that it achieves state-of-the-art recommendation accuracy and generates more coherent and informative conversations.

Towards Natural Language Interfaces for Data Visualization: A Survey.

Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary input modality to direct manipulation for visual analytics can provide an engaging user experience. It enables users to focus on their tasks rather than having to worry about how to operate visualization tools on the interface. In the past two decades, leveraging advanced natural language processing technologies, numerous V-NLI systems have been developed in academic research and commercial software, especially in recent years. In this article, we conduct a comprehensive review of the existing V-NLIs. In order to classify each article, we develop categorical dimensions based on a classic information visualization pipeline with the extension of a V-NLI layer. The following seven stages are used: query interpretation, data transformation, visual mapping, view transformation, human interaction, dialogue management, and presentation. Finally, we also shed light on several promising directions for future work in the V-NLI community.

College Enquiry Chatbot using Conversational AI

Abstract: Chatbots are computer programs that use text or voice-based interfaces to replicate human conversation. They are often used to automate mundane processes, provide customer support, or aid in the retrieval of information. Chatbots are built with a number of strategies that enable them to interpret and respond to user inputs in a more human-like manner. They can be employed in a variety of industries, including e-commerce, healthcare, and banking. We have analysed and compared numerous chatbot strategies in this report to establish the optimal way for our own chatbot project. We reviewed twenty-six papers on chatbot development and assessed the advantages and disadvantages of various strategies. Natural language processing techniques, such as tokenization and named entity recognition, have been shown in our research to be critical for interpreting user inputs. We also discovered that dialogue management methods, such as rule-based and machine learning-based approaches, have an important influence in influencing discussion flow. Furthermore, we discovered that natural language generation techniques, such as template-based and neural network-based methods, are critical in generating effective chatbot responses. We also investigated various services on the market in order to create a functional chatbot for our college. We also emphasized the various applications of chatbots as well as the current hurdles in the industry. Based on these findings, we chose a technique for our own chatbot project that employs advanced natural language processing and machine learning techniques to create more human-like conversations and improve overall user experience.

Dialogue Act Classification via Transfer Learning for Automated Labeling of Interviewee Responses in Virtual Reality Job Interview Training Platforms for Autistic Individuals

Computer-based job interview training, including virtual reality (VR) simulations, have gained popularity in recent years to support and aid autistic individuals, who face significant challenges and barriers in finding and maintaining employment. Although popular, these training systems often fail to resemble the complexity and dynamism of the employment interview, as the dialogue management for the virtual conversation agent either relies on choosing from a menu of prespecified answers, or dialogue processing is based on keyword extraction from the transcribed speech of the interviewee, which depends on the interview script. We address this limitation through automated dialogue act classification via transfer learning. This allows for recognizing intent from user speech, independent of the domain of the interview. We also redress the lack of training data for a domain general job interview dialogue act classifier by providing an original dataset with responses to interview questions within a virtual job interview platform from 22 autistic participants. Participants’ responses to a customized interview script were transcribed to text and annotated according to a custom 13-class dialogue act scheme. The best classifier was a fine-tuned bidirectional encoder representations from transformers (BERT) model, with an f1-score of 87%.

Determination of Priorities for the Development of Small and Medium Enterprises in the Province of South Sulawesi Using the Weighted Product Model

Small and Medium Enterprises (SMEs) are a sector that plays a vital role in running the national economy. The South Sulawesi Provincial Office of Industry as a regional government organization is tasked with administering affairs in the industrial sector of the South Sulawesi Province. In terms of developing SMEs, the South Sulawesi Provincial Industry Service has the right to determine priority industries that have the potential to be developed. The decision-making process at the South Sulawesi Industry Office is still experiencing several obstacles. This is due to the decision making does not use an objective method. In order to help solve this problem, we need a system that can be used to determine industrial development priorities. This research builds a web-based decision support system software regarding priority setting for SMEs development in South Sulawesi Province using the weighted product model. A method that will find a concluding solution by considering industry weights and criteria. This study uses the implementation of the data management subsystem using MySQL. Meanwhile, the implementation of the model management subsystem uses the weighted product model and the dialog management subsystem uses a website interface that can assist the South Sulawesi Provincial Office of Industry in determining priorities for the development of SMEs.

Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots by Michael McTear

Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots by Michael McTear

Dialogue Management and Language Generation for a Robust Conversational Virtual Coach: Validation and User Study.

Designing human-machine interactive systems requires cooperation between different disciplines is required. In this work, we present a Dialogue Manager and a Language Generator that are the core modules of a Voice-based Spoken Dialogue System (SDS) capable of carrying out challenging, long and complex coaching conversations. We also develop an efficient integration procedure of the whole system that will act as an intelligent and robust Virtual Coach. The coaching task significantly differs from the classical applications of SDSs, resulting in a much higher degree of complexity and difficulty. The Virtual Coach has been successfully tested and validated in a user study with independent elderly, in three different countries with three different languages and cultures: Spain, France and Norway.