Conversational Assistants Research Articles

Deriving comprehensive literature trends on multi-omics analysis studies in autism spectrum disorder using literature mining pipeline

Autism spectrum disorder (ASD) is characterized by highly heterogenous abnormalities in functional brain connectivity affecting social behavior. There is a significant progress in understanding the molecular and genetic basis of ASD in the last decade using multi-omics approach. Mining this large volume of biomedical literature for insights requires considerable amount of manual intervention for curation. Machine learning and artificial intelligence fields are advancing toward simplifying data mining from unstructured text data. Here, we demonstrate our literature mining pipeline to accelerate data to insights. Using topic modeling and generative AI techniques, we present a pipeline that can classify scientific literature into thematic clusters and can help in a wide array of applications such as knowledgebase creation, conversational virtual assistant, and summarization. Employing our pipeline, we explored the ASD literature, specifically around multi-omics studies to understand the molecular interplay underlying autism brain.

Framework to enable and test conversational assistant for APIs and RPAs

AbstractIn the realm of business automation, conversational assistants are emerging as the primary method for making automation software accessible to users in various business sectors. Access to automation primarily occurs through application programming interface (APIs) and robotic process automation (RPAs). To effectively convert APIs and RPAs into chatbots on a larger scale, it is crucial to establish an automated process for generating data and training models that can recognize user intentions, identify questions for conversational slot filling, and provide recommendations for subsequent actions. In this paper, we present a technique for enhancing and generating natural language conversational artifacts from API specifications using large language models (LLMs). The goal is to utilize LLMs in the “build” phase to assist humans in creating skills for digital assistants. As a result, the system does not need to rely on LLMs during conversations with business users, leading to efficient deployment. Along with enabling digital assistants, our system employs LLMs as proxies to simulate human interaction and automatically evaluate the digital assistant's performance. Experimental results highlight the effectiveness of our proposed approach. Our system is deployed in the IBM Watson Orchestrate product for general availability.

Need of retrieval augmented generation for conversational assistants for government social welfare scheme popularization

Governments allocate substantial resources to uplift under-privileged communities through various assistance schemes. Despite these efforts, the effectiveness of such initiatives often fails due to variety of reasons including cryptic nature of information available, lack of awareness to the needy people and or lack of transparency. In India, a vast and diverse developing democracy, these challenges are exacerbated by disparities in access to information. To address these issues, we explored the use of conversational AI technologies, including chatbots, which have seen successful application in many developed nations. Conversational AI agents often get challenged to a variety of factual inaccuracies and other types of hallucinations. Our study compares the accuracy of responses across different architectures: Our architectures integrate advancements in natural language processing, such as large language models (LLMs) and retrieval-augmented generation (RAG), along with automatic speech recognition (ASR), knowledge distillation, hybrid retrieval strategies, and text-to-speech systems. Overall this research experiments demonstrate that leveraging retrieval augmented generation using the same model embeddings substantially improves the quality of the output, its similarity to desired responses. This also reduces hallucinations. We also notice that larger models perform better than smaller parameter models.

Using Artificial Intelligence Tools for Developing Conversational Skills for English Majors

Despite the potential of Virtual Conversation Assistants as effective tools for conversing support in developing students’ conversational skills, their presence in Vietnamese schools or universities remains limited, often due to cost constraints, quality of language interaction, and their unpopularity among Vietnamese students. Therefore, it is essential that English language educators seek alternative strategies to offer additional assistance for the enhancement of students' abilities to converse effectively. This experimental study pilots the implementation of Call Annie and Praktika, two artificial intelligence (AI) technologies in a local teacher education university in Vietnam, as an innovative approach to the fostering of students' conversational skills. The research discusses the utilization of two such virtual conversational assistant tools for a group of 14 English major freshmen as the experimental group, examining their impacts on the development of students’ conversational proficiency compared to another 14 students in the control group. The study findings analyzed indicate that there was a remarkable improvement in the experimental group’s conversational skills regarding their initiation of conversation, and their active listening through two AI tools. Moreover, there was also remarkable improvement in their verbal fluency and clarity; which contributed to their adaptability, flexibility, and conversational engagement. Moreover, it suggests further application of AI tools in educational contexts to facilitate the instruction and reinforcement of students' conversational skills, where human expertise seamlessly integrates with the power of AI tools to create a more effectively expanded language learning environment.

On Replacing Humans with Large Language Models in Voice-Based Human-in-the-Loop Systems

It is easy to assume that Large Language Models (LLMs) will seamlessly take over applications, especially those that are largely automated. In the case of conversational voice assistants, commercial systems have been widely deployed and used over the past decade. However, are we indeed on the cusp of the future we envisioned? There exists a social-technical gap between what people want to accomplish and the actual capability of technology. In this paper, we present a case study comparing two voice assistants built on Amazon Alexa: one employing a human-in-the-loop workflow, the other utilizes LLM to engage in conversations with users. In our comparison, we discovered that the issues arising in current human-in-the-loop and LLM systems are not identical. However, the presence of a set of similar issues in both systems leads us to believe that focusing on the interaction between users and systems is crucial, perhaps even more so than focusing solely on the underlying technology itself. Merely enhancing the performance of the workers or the models may not adequately address these issues. This observation prompts our research question: What are the overlooked contributing factors in the effort to improve the capabilities of voice assistants, which might not have been emphasized in prior research?

Optimizing Higher Education Using Artificial Intelligence

A revolutionary transformation and overhaul of our approach to how we instruct and interact with educational content is being heralded by the simultaneous development of artificial intelligence and education. Businesses dealing with educational technology are greatly engaging and spending exponentially over technologies delivering education by artificial intelligence. Such technologies generate highly interactive and deeply engaging educational experiences for the learners creating an everlasting impact. Some of the cutting-edge technologies that improve student engagement and encourage deeper connections with the educational content or the conversational assistants that interact verbally and virtually. Virtual reality (VR), Augmented reality (AR), holographic simulations, etc. are some more examples of AI generated applications which are now being used to create immersive learning experiences. This paper explores the role of AI in higher education, it’s benefits for both learners & educators, it’s application in H.E. classrooms, utilisation of AI-detection technology, challenges and strategies to implement AI seamlessly in educational settings. It is an effort made in order to discuss this emerging topic and to offer an insight into the constantly evolving relationship between AI an education.

AI-POWERED PEDAGOGY: FOREIGN LANGUAGE STUDY IN HIGHER EDUCATION

The paper explores the transformative role of Artificial Intelligence (AI) in foreign language study within the context of higher education. It discusses how AI has redefined traditional teaching methods by introducing innovative pedagogical tools. Through an in-depth analysis, the research illustrates the enhancement of communicative capabilities, where AI significantly improves the interaction dynamics in the target language among students. Presently, AI-driven language platforms enable personalized learning, catering to individual strengths and cultural backgrounds. However, concerns emerge about the potential erosion of traditional teaching roles in the face of AI’s capabilities. Yet, for AI to enhance the learning process, educators must possess robust digital competencies to effectively leverage AI technologies. Furthermore, the utilization of AI enables the customization of learning experiences, adapting to individuals’ needs, propensities, and skill levels, thus fostering motivation and commitment to language acquisition. AI’s capability to offer immediate and precise feedback is also highlighted as a critical factor in expediting the learning process and easing the anxiety related to performance evaluation. Moreover, the emergence of intelligent conversational assistants is showcased as a pivotal development in the domain. These AI-driven language bots act as virtual language partners, offering realistic conversation practice and proficiency evaluations that contribute to a supportive and boundless learning environment. While acknowledging the substantial benefits of AI in foreign language education, the paper concludes by reaffirming the irreplaceable role of human teachers as the central organizers of the educational process. It is implied that the successful integration of AI in language pedagogy rests upon its alignment with conventional teaching practices guided by experienced educators.

HOMMIE: CONVERSATIONAL AI ASSISTANT

Conversational AI assistants have witnessed remarkable progress in recent years, transforming human-computer interaction across a spectrum of applications. This paper offers a comprehensive overview of the state-of-the-art techniques, methodologies, and challenges in the field. We examine the core components of conversational AI, including natural language understanding, dialogue management, and response generation. Additionally, we address key challenges such as context modeling, personalization, and ethical considerations. The paper serves as a roadmap for researchers and developers, highlighting current achievements and avenues for future advancements in the dynamic domain of conversational AI. keyword - Conversational AI, NLP, Assistant, Machine Learning, Chatbot

AI Study Partner : Development of an LLM and Gen AI-Enhanced Study Assistant Tool

In recent years, Generative AI has started to play a pivotal role in transforming the educational landscape, making learning more personalized, engaging, and accessible. Unlike traditional educational tools, Gen AI can adapt to each student's unique learning style and pace, offering customized support that can significantly enhance understanding and retention of information. It enables the creation of intelligent tutoring systems, interactive study aids, and personalized learning experiences that can assess and respond to individual needs in real time This paper introduces the AI Study Partner, an innovative tool designed to revolutionize the educational landscape by integrating Generative Artificial Intelligence (Gen AI) and Large Language Models (LLMs). The AI Study Partner is engineered to cater to the diverse needs of learners by offering a suite of six key features: the ability to upload and interact with any type of content, summarization of extensive lessons, generation of flashcards for effective study, automated question creation with auto-evaluation capabilities, a conversational chatbot assistant, and an advanced smart search function. These features collectively aim to create a more personalized, engaging, and efficient learning experience. The development of the AI Study Partner responds to the pressing need for educational tools that accommodate the varying paces and styles of learning, making education more accessible and effective. By leveraging the latest advancements in AI, the tool not only facilitates a deeper understanding of complex subjects but also encourages independent study habits and critical thinking skills. This research outlines the conceptual framework, design methodology, and technical implementation of the AI Study Partner, highlighting its potential to positively impact education by providing a versatile and interactive learning platform.The AI Study Partner represents a significant step forward in the pursuit of creating adaptive, responsive, and personalized educational experiences for learners worldwide. Key Words : Artificial Intelligence in Education, Personalized Learning , Large Language Models (LLMs), Generative AI (Gen AI), User Engagement in Learning Data-Driven Education, Vector database, AI based Feedback Conversational Chatbots, Smart Search.

ESG Accountability Made Easy: DocQA at Your Service

We present Deep Search DocQA. This application enables information extraction from documents via a question-answering conversational assistant. The system integrates several technologies from different AI disciplines consisting of document conversion to machine-readable format (via computer vision), finding relevant data (via natural language processing), and formulating an eloquent response (via large language models). Users can explore over 10,000 Environmental, Social, and Governance (ESG) disclosure reports from over 2000 corporations. The Deep Search platform can be accessed at: https://ds4sd.github.io.

A Systematic Review of Fairness, Accountability, Transparency and Ethics in Information Retrieval

We live in an information society that strongly relies on information retrieval systems, such as search engines and conversational assistants. Consequently, the trustworthiness of these systems is of critical importance, and has attracted a significant research attention in recent years. In this work, we perform a systematic literature review of the field of fairness, accountability, transparency, and ethics in information retrieval. In particular, we investigate the definitions, approaches, and evaluation methodologies proposed to build trustworthy information retrieval systems. This review reveals the lack of standard definitions, arguably due to the multi-dimensional nature of the different notions. In terms of approaches, most of the work focuses on building either a fair or a transparent information retrieval system. As for evaluation, fairness is often assessed by means of automatic evaluation, while accountability and transparency are most commonly evaluated using audits and user studies. Based on the surveyed literature, we develop taxonomies of requirements for the different notions, and further use these taxonomies to propose practical definitions to quantify the degree to which an information retrieval system satisfies a given notion. Finally, we discuss challenges that have yet to be solved for information retrieval systems to be trustworthy.

Investigating the Impact of Automation on the Health Care Workforce Through Autonomous Telemedicine in the Cataract Pathway: Protocol for a Multicenter Study.

While digital health innovations are increasingly being adopted by health care organizations, implementation is often carried out without considering the impacts on frontline staff who will be using the technology and who will be affected by its introduction. The enthusiasm surrounding the use of artificial intelligence (AI)-enabled digital solutions in health care is tempered by uncertainty around how it will change the working lives and practices of health care professionals. Digital enablement can be viewed as facilitating enhanced effectiveness and efficiency by improving services and automating cognitive labor, yet the implementation of such AI technology comes with challenges related to changes in work practices brought by automation. This research explores staff experiences before and after care pathway automation with an autonomous clinical conversational assistant, Dora (Ufonia Ltd), that is able to automate routine clinical conversations. The primary objective is to examine the impact of AI-enabled automation on clinicians, allied health professionals, and administrators who provide or facilitate health care to patients in high-volume, low-complexity care pathways. In the process of transforming care pathways through automation of routine tasks, staff will increasingly "work at the top of their license." The impact of this fundamental change on the professional identity, well-being, and work practices of the individual is poorly understood at present. We will adopt a multiple case study approach, combining qualitative and quantitative data collection methods, over 2 distinct phases, namely phase A (preimplementation) and phase B (postimplementation). The analysis is expected to reveal the interrelationship between Dora and those affected by its introduction. This will reveal how tasks and responsibilities have changed or shifted, current tensions and contradictions, ways of working, and challenges, benefits, and opportunities as perceived by those on the frontlines of the health care system. The findings will enable a better understanding of the resistance or susceptibility of different stakeholders within the health care workforce and encourage managerial awareness of differing needs, demands, and uncertainties. The implementation of AI in the health care sector, as well as the body of research on this topic, remain in their infancy. The project's key contribution will be to understand the impact of AI-enabled automation on the health care workforce and their work practices. PRR1-10.2196/49374.

Evaluating Critical Success Factors for Acceptance of Digital Assistants for Online Shopping Using Grey–DEMATEL

Conversational digital assistants (CDAs), driven by artificial intelligence, are emerging innovative technologies to assist customers with online shopping. Despite the benefits of CDAs, customers resist their use for online shopping. Hence, studying what factors motivate consumers to adopt OSAs is necessary. The study first identifies twelve CDA acceptance factors through a literature review and expert opinion. It then uses a unique grey-DEMATEL method to evaluate the cause-and-effect relationships among the factors. The grey-DEMATEL approach effectively analyzes causal interactions among elements, overcoming the bias of imprecise human judgments in real life. The authors find that the critical cause factors that affect other factors of CDAs’ adoption are anxiety, trust, social presence, enjoyment, and humanness. Managers and policymakers can use the study’s findings to drive CDAs’ acceptance. The study uniquely identifies the critical success factors for CDAs’ acceptance for online shopping and analyzes their causal relations in a grey environment.

Utilizing User Preferences in Designing the AGILE (Accelerating Access to Gender-Based Violence Information and Services Leveraging on Technology Enhanced) Chatbot.

Technology advancements have enhanced artificial intelligence, leading to a user shift towards virtual assistants, but a human-centered approach is needed to assess for acceptability and effectiveness. The AGILE chatbot is designed in Kenya with features to redefine the response towards gender-based violence (GBV) among vulnerable populations, including adolescents, young women and men, and sexual and gender minorities, to offer accurate and reliable information among users. We conducted an exploratory qualitative study through focus group discussions (FGDs) targeting 150 participants sampled from vulnerable categories; adolescent girls and boys, young women, young men, and sexual and gender minorities. The FGDs included multiple inquiries to assess knowledge and prior interaction with intelligent conversational assistants to inform the user-centric development of a decision-supportive chatbot and a pilot of the chatbot prototype. Each focus group comprised 9-10 members, and the discussions lasted about two hours to gain qualitative user insights and experiences. We used thematic analysis and drew on grounded theory to analyze the data. The analysis resulted in 14 salient themes composed of sexual violence, physical violence, emotional violence, intimate partner violence, female genital mutilation, sexual reproductive health, mental health, help-seeking behaviors/where to seek support, who to talk to, and what information they would like, features of the chatbot, access of chatbot, abuse and HIV, family and community conflicts, and information for self-care. Adopting a human-centered approach in designing an effective chatbot with as many human features as possible is crucial in increasing utilization, addressing the gaps presented by marginalized/vulnerable populations, and reducing the current GBV epidemic by moving prevention and response services closer to people in need.

Conversational assistants in academic libraries: enhancing reference services through Bing Chat

Purpose This research aims to explore the integration of Bing Chat, an artificial intelligence (AI)-powered conversational assistant, into academic libraries and its potential impact on reference services. Design/methodology/approach This study analyzes existing literature to investigate the integration of Bing Chat in academic libraries. This research focuses on its features, capabilities and implications for enhancing user experiences and addressing information needs. Findings The findings highlight that Bing Chat’s conversational interface facilitates more dynamic and context-aware reference interactions, fostering user empowerment and personalized learning pathways. The integration of Bing Chat with existing library resources enhances resource discovery, navigational assistance and engagement with visual content. However, challenges related to accuracy, privacy and algorithmic bias require careful consideration. Originality/value This research contributes to the literature by providing an in-depth exploration of Bing Chat’s integration into academic libraries, emphasizing its transformative potential for reference services. This study addresses ethical and social dimensions associated with AI-driven tools in library environments, offering insights into ensuring fairness, privacy and user trust.

Designing a Chatbot for Contemporary Education: A Systematic Literature Review

A chatbot is a technological tool that can simulate a discussion between a human and a program application. This technology has been developing rapidly over recent years, and its usage is increasing rapidly in many sectors, especially in education. For this purpose, a systematic literature review was conducted using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework to analyze the developments and evolutions of this technology in the educational sector during the last 5 years. More precisely, an analysis of the development methods, practices and guidelines for the development of a conversational tutor are examined. The results of this study aim to summarize the gathered knowledge to provide useful information to educators that would like to develop a conversational assistant for their course and to developers that would like to develop chatbot systems in the educational domain.

The adoption of conversational assistants in the banking industry: is the perceived risk a moderator?

The world has noticed tremendous growth in information technology, particularly the Internet of Things and artificial intelligence. Nowadays, a lot of people rely on conversational assistants (CAs) and other intelligent virtual objects to check account balances, communicate more quickly, make payments, and manage their financial assets with banks or other financial institutions. This study scrutinizes how consumers espouse and utilize conversational assistants in banking amenities. To provide empirical evidence and generalize sample results in a larger context, a quantitative research approach has been utilized. A structured questionnaire was prepared, which generates 181 participants. The questionnaire was selected for its suitability in systematically capturing consumers' perceptions and intentions. According to the findings of partial least square structural equation modeling (PLS-SEM), perceived ease of use (PEOU), perceived enjoyment (PE), and perceived trust (PT) have significant impacts on users' intentions to use conversational assistants, however, perceived usefulness (PU) does not have any significant effects. Furthermore, the relationship between PEOU and intention is significantly and negatively moderated by perceived risk (PR). By enabling stakeholders to create strategies that improve customer experience and unleash the full potential of conversational assistants in banking services, these findings help to better understand consumer behavior.

Creative Use of OpenAI in Education: Case Studies from Game Development

Educators and students have shown significant interest in the potential for generative artificial intelligence (AI) technologies to support student learning outcomes, for example, by offering personalized experiences, 24 h conversational assistance, text editing and help with problem-solving. We review contemporary perspectives on the value of AI as a tool in an educational context and describe our recent research with undergraduate students, discussing why and how we integrated OpenAI tools ChatGPT and Dall-E into the curriculum during the 2022–2023 academic year. A small cohort of games programming students in the School of Computing and Digital Media at London Metropolitan University was given a research and development assignment that explicitly required them to engage with OpenAI. They were tasked with evaluating OpenAI tools in the context of game development, demonstrating a working solution and reporting on their findings. We present five case studies that showcase some of the outputs from the students and we discuss their work. This mode of assessment was both productive and popular, mapping to students’ interests and helping to refine their skills in programming, problem-solving, critical reflection and exploratory design.

Evaluation of Replies to Voice Queries in Gynecologic Oncology by Virtual Assistants Siri, Alexa, Google, and Cortana

Women that receive news that they have a malignancy of gynecologic origin can have questions about their diagnosis. These questions might be posed as voice queries to the virtual assistants Siri, Alexa, Google, and Cortana. Because our world has increasingly adopted smart phones and standalone voice query devices, this study focused on the accuracy of audible replies by the virtual assistants (VAs) Siri, Alexa, Google, and Cortana to voice queries related to gynecologic oncology. Twenty-one evaluators analyzed VA audible answers to select voice queries related to gynecologic oncology. Questions were posed in three different ways for each voice query in order to maximize the likelihood of acceptability to the VAs in a 24-question panel. For general queries that were not related to gynecologic oncology, Google provided the most correct audible replies (83.3% correct), followed by Alexa (66.7% correct), Siri (45.8% correct), and Cortana (20.8% correct). For gynecologic oncology-related queries, the accuracy of the VAs was considerably lower: Google provided the most correct audible replies (18.1%), followed by Alexa (6.5%), Siri (5.5%), and Cortana (2.3%). There was a considerable drop in the accuracy of audible replies to oral queries on topics in gynecologic oncology relative to general queries that were not related to gynecologic oncology. There is considerable room for improvement in VA performance, so that caution is advised when using VAs for medical queries in gynecologic oncology. Our specific findings related to gynecologic oncology extend the work of others with regard to the low usability of general medical information obtained from VAs, so that reliance on conversational assistants for actionable medical information represents a safety risk for patients and consumers.

Task2KB: A Public Task-Oriented Knowledge Base

Search engines and conversational assistants are commonly used to help users complete their every day tasks such as booking travel, cooking, etc. While there are some existing datasets that can be used for this purpose, their coverage is limited to very few domains. In this paper, we propose a novel knowledge base, ‘Task2KB’, which is constructed using data crawled from WikiHow, an online knowledge resource offering instructional articles on a wide range of tasks. Task2KB encapsulates various types of task-related information and attributes, such as requirements, detailed step description, and available methods to complete tasks. Due to its higher coverage compared to existing related knowledge graphs, Task2KB can be highly useful in the development of general purpose task completion assistants.