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 73 for “"User intent"”.
-
Computational user intent modeling
User modeling is essential for any information service system (e.g., search engines, recommender systems, and computational advertising) to optimize its service to the end users. The level of user understanding directly determines the upper bound of optimality that such a system can achieve when …
-
Adapting Models to User Intent for Robust and Controllable Generation
… remain responsive to complex and dynamic human intentions. However, this same architectural flexibility inadvertently leaves them vulnerable to manipulation by bad actors and unintended changes. To ensure AI remains an empowering tool rather than a fragile liability, this dissertation presents a …
-
Integration of Electromyography-Based Detection of User Intent for Control of an Assistive Glove
… Glove is a semi-rigid device intended to aid users with Spinal Cord Injury (SCI) to achieve common hand poses that are necessary to complete Activities of Daily Living (ADL). Previously, operation of the glove required an experimenter to command each motor individually to actuate the glove's …
-
Few-Shot User Intent Detection and Response Selection for Conversational Dialogue System Using Deep Learning
… apps, websites, and mobile apps to engage with users through natural language. The primary objective of chatbots is to facilitate communication with people and make numerous repetitious tasks easier for humans. This thesis investigates the application of deep learning methodologies in enterprise …
-
Improving User Sparse Query Interpretation Through Pseudo-Relevance Retrieval Methods
… retrieval technology, understanding sparse user query remains a significant challenge. Users often input short, ambiguous, or context-lacking queries when searching, making it difficult for retrieval systems to capture user intent. This thesis focuses on this critical issue and proposes …
-
Towards Intelligent Conversational Assistants: Enhancing Task-Oriented Dialogue Systems with Knowledge Integration
… intelligent assistants’ ability to understand user intent and execute structured tasks. While recent advancements in Natural Language Processing (NLP) and Large Language Models (LLMs) have significantly improved dialogue systems, TOD systems still face critical challenges in knowledge …
-
Understanding and supporting AI alignment in graphic design
… and digital media, brand styles, and graphical user interfaces for both professional and personal use. As a visual form of communication, graphic design is a widespread practice, and both professional designers and novices increasingly utilize artificial intelligence (AI) to support it. However, …
-
Multimodal Conversational AI: Understanding, Reasoning, and Generation
… that understand multimodal inputs, reason about user intent, and generate expressive audio-visual responses. Our contributions are organized along three stages of the conversational pipeline---Understanding, Reasoning, and Generation---unified by two cross-cutting methodological themes: modality …
-
Distributed context discovering for predictive modeling
… as advertising, search and online sales. Usually user-intent information such as query terms and previous click history is used in click prediction. However, this information is not always available. For example, there are no queries from users on the webpages of content publishers, such as …
-
On the Security and Privacy of Web Requests
… issues. First, we investigate the risks posed by user-impersonation attacks, where client-side malware forges or tampers with web requests, initiating security-sensitive actions such as financial transactions or voting without the user’s true intent. Current defenses, including user authentication …
-
A brain-machine interface for assistive robotic control
… loss of voluntary motor control. By inferring user intent from task-modulated neurological signals and then translating those intentions into actions, BMIs can enable LIS patients increased autonomy. Significant effort has been devoted to developing BMIs over the last three decades, but only …
-
Continuous Myoelectric Prediction of Future Ankle Kinematics and Kinetics for the Control of Active Powered Prostheses
… predictive model of gait that incorporates user intent, vis-à-vis surface electromyography (EMG) signals of the lower limb, to continuously predict future ankle kinematics and kinetics across multiple terrains and their transitions for the control of an active ankle-foot prosthesis. …
-
User-Guided Deep Multiple Clustering
… lead to results that do not match the aspects users care about. This dissertation proposes a user-preference guided framework for deep multiple clustering that aims to obtain partitions that are both diverse and aligned with user interests, and is organized into four contributions that start …
-
Ablative study of large language model-based gesture inference for autonomous navigation
… only perform gesture inference but can propose user intent provided with a context and list of possible actions. We propose an ablative study of an LLM based gesture inference system applied to the context of guiding an autonomous agent through a maze. Measuring distance from the goal, inference …
-
SOFT ACTUATORS AND SENSORS FOR WEARABLE ROBOTICS
… have been used for wearable interfaces to detect user intent. These are light and conformal, leading to less discomfort than conventional sensors. However, they are slow and not robust to noise. Soft actuators while safe to deploy on the human body need high pressures to generate the force output …
-
ENHANCING CONVERSATIONAL AGENTS: SOURCE-AWARE GENERATION AND CONVERSATIONAL PARTNER UNDERSTANDING
… it strengthens memory tracking to improve user intent comprehension. In multi-agent interactions, it employs a probabilistic graphical model to enhance mutual dialogue memory, enabling agents to navigate strategic collaboration and competition. Overall, this work advances conversational AI …
-
How to Use Brains and Computers to Enhance Brain Computer Interfacing
… brain data in real-time, BCIs can translate user intent into actionable commands that can control computer cursors, wheelchairs, and robotic arms. However, many individuals struggle to learn how to control these devices. In this investigation, we explore two methods to improve brain computer …
-
DESIGN PROBES FOR AI−DRIVEN AAC: ADDRESSING COMPLEX COMMUNICATION NEEDS IN APHASIA
… challenges, such as occasional mismatches with user intent, findings demonstrate how AI’s specific capabilities can be advantageous in addressing PWAs’ complex needs. Our work contributes design insights for future Augmentative and Alternative Communication (AAC) systems.
-
FROM PASSIVE BROWSING TO ADAPTIVE INTERACTION: A HYBRID ONLINE SHOPPING FRAMEWORK
Traditional e-commerce systems rely on user queries and implicit interactions that may not accurately capture user intent, while conversational approaches impose excessive interaction burden. A hybrid shopping paradigm is introduced to bridge this gap, preserving the familiar browsing experience …
Page 1 of 4