Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 33 for “"Conversational systems"”.
-
Incorporating non-verbal modalities in spoken language understanding for multimodal conversational systems
Thesis (Ph. D.)--Michigan State University. Computer Science, 2009
-
Psychological vulnerabilities and user behaviour under adversarial techniques in text-based conversational systems
Conversational systems have become increasingly embedded in our daily interactions across domains such as healthcare, e-commerce, education, and customer service. While these systems offer benefits for accessibility and user experience, they also introduce opportunities for manipulation that can …
-
Designing Engaging Conversational Interactions for Health & Behavior Change
The recent popularity of chat and voice-based conversational interactions fueled by advances in natural language processing (NLP) has opened up opportunities for re-imagining user interactions in health & behavior change as conversational experiences. Prior work has indicated that a well-designed …
-
AI-Serve: Empowering Service Provisioning with Conversational and Generative AI
The global conversational AI market has been growing rapidly with widely adopted applications in diverse domains, including customer service, finance, education, and healthcare. Voice-enabled assistants such as Siri, Alexa, and Google Assistant are used by hundreds of millions of people worldwide …
-
Spoken Language Understanding: from Spoken Utterances to Semantic Structures
… These two projects defined a first generation of conversational systems. In late nineties ``How may I help you'' project from AT\&T, with Large Vocabulary Continuous Speech Recognition (LVCSR) and mixed initiatives spoken interfaces, started the second generation of conversational systems, which …
-
Feature and classification analyses of the electroencephalogram (EEG) recorded during the perception and production of emotional vocalisations
… access to physiological data for intelligent conversational systems to infer emotion from users and provide emotion-aware conversations. Using EEG could also potentially benefit patients with limited motor functionalities, who can only perform imagined utterances. Understanding EEG features …
-
Trustworthy, Socially Responsible, and Knowledge-Grounded Conversational AI
… advancements have been made in open-domain conversational agents powered by Large Language Models (LLMs) trained on vast and diverse datasets. State-of-the-art LLMs like GPT-4, Claude, and LLaMA have enabled conversational systems capable of engaging in prolonged discussions on virtually any …
-
ADVANCES IN CONVERSATIONAL AND TIME-SENSITIVE QUESTION ANSWERING
… the need for robust question answering (QA) systems is increasingly critical. While large language models have advanced QA capabilities, they continue to face significant challenges in maintaining coherent conversations and adapting to rapidly evolving real-world facts. This thesis …
-
Do I Know You? Evaluating Human-to-Human Authentication via Conversational Interfaces
… human-to-human authentication methods in conversational systems. We evaluate each theme and rank them based on data source access and analysis complexity. While we find that many strategies can only provide weak security guarantees, we also identify one that could provide strong guarantees …
-
Τεχνητή νοημοσύνη και τεχνικές σκαλωσιάς στη διδασκαλία φυσικών επιστημών
… the design principles and applications of conversational systems in education. In the empirical part, the PhysicsBot was developed in three successive versions (V1.0, V1.1, V1.2). The pilot phase included preliminary experiments with ChatGPT and an independent platform (V1.1), while the …
-
Evaluating Function Calling in Language Models through a Conversational Agent
… in Large Language Models (LLMs) for data-driven conversational systems. While LLMs excel in natural language understanding, reliably mapping user queries to structured computational functions remains a key challenge. To address this, the study develops the India Policy Insights (IPI) Chatbot, a …
-
Hugrún : Runtime-Governed Therapeutic Interaction for LLM-Based CBT Systems
… language models (LLMs) can support structured conversational systems for digital mental health applications. Although modern LLMs can generate fluent and empathetic dialogue, unconstrained generative behavior presents significant challenges to maintaining coherent therapeutic progression, …
-
A Universal Chatbot Platform for Data Science: Bridging the Gap between Large Language Models and Knowledge Graphs
… with structured KG reasoning to enable conversational access to arbitrary KGs. This thesis tackles this challenge through three progressive milestones. First, to establish the foundation for universal KG access, we eliminate expensive preprocessing on KGs and domain specific training. We …
-
Automated semantic grammar generation in dialogue-based task-oriented systems
Dialogue-base task-oriented systems are conversational systems that can complete tasks and answer questions. A semantic grammar can be helpful for user input recognition in such systems. Manually creating semantic grammars can be cumbersome for a developer and delay the deployment of the system, …
-
Adaptive Human-Chatbot Interactions: Contextual Factors, Variability Design and Levels of Automation
… In this dynamic environment, modern software systems interact with numerous external systems, interfaces, data sources, and work practices. This complexity requires developers to navigate a complex environment while creating software. Adding to this landscape is the emergence of AI-based …
-
Towards Improved Conversation Context Understanding for Effective Conversational Information Retrieval
Conversational Information Retrieval (CIR) has garnered considerable attention in recent years. A key challenge in CIR is formulating effective queries during the dialogue between the searcher and the conversational agent. Unlike traditional information retrieval systems, where users independently …
-
Neural Sequence Labeling on Social Media Text
… This polyglot environment requires modern systems to adapt to a diverse range of languages, imposing another linguistic barrier to processing and understanding of text from SM domains. This thesis aims at providing novel sequence labeling approaches to handle noise and linguistic …
-
Multimodal Conversational AI: Understanding, Reasoning, and Generation
… form of human communication, yet building AI systems that can engage in rich, multimodal dialogue remains a fundamental challenge. This thesis develops techniques for multimodal conversational AI---systems that understand multimodal inputs, reason about user intent, and generate expressive …
-
Examining the potential for enhancing User experience in exploratory search using conversational agent support
… and corresponding effective queries. The conversational search seeks to enable the next generation of more natural and efficient search applications that should be easy to use while less cognitively demanding on searchers. Since conversation is a natural means of human information inquiry, …
-
Towards Building a Theory-Grounded and Steerable Emotional Support Conversational AI
… for scalable and reliable mental-health support systems. At the same time, large language models (LLMs) are rapidly transforming human–computer interaction, offering the potential to augment—not replace—traditional emotional support. Yet, deploying these systems responsibly requires ensuring that …
Page 1 of 2