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 169 for “"NLU"”.
-
Characterization of thermal damage in 2205 duplex stainless steel with nonlinear ultrasonics (nlu)
… stainless steel using nonlinear ultrasonics (NLU). Seven 2205 duplex stainless steel specimens are thermally degraded at 700 C for a series of different time durations. Nonlinear Ultrasonic measurements are conducted in a pitch-catch setup to avoid any adverse nonlinear influences of …
-
Knowledge and Ontology Enhanced Approach to Natural Language Understanding (KOE-NLU) in Computational Social Media and Healthcare
Natural Language Understanding (NLU) faces both opportunities and challenges as the amount of social media and healthcare data grows. This is particularly evident in context-sensitive applications such as evaluating cognitive health, identifying mental health symptoms, and monitoring drug abuse. …
-
Fuse and Adapt: Investigating the Use of Pre-Trained Self-Supervising Learning Models in Limited Data NLU problems
… in the field of Natural Language Understanding (NLU). NLU is the ability of machines to understand human language. It has enabled many practical applications such as Emotion Recognition, Sentiment Analysis, Summarization, and Question Answering. This thesis mainly explores the utilization of …
-
Intent Based Utterance Segmentation for Multi IntentNLU
Natural Language Understanding(NLU) is a process of converting the user utterance to a dialog-act after identifying domain, intent and slots from the utterance. User utterances can either contain a single intent or could express multiple intents. Building an NLU module for multi-intent utterances …
-
Applying and Improving Non-Linear Ultrasonic Techniques for Robust Inspection of Concrete and Polymer Composite Materials
… this dissertation a new Non-Linear Ultrasonic (NLU) technique for monitoring progression of curing in concrete specimens, estimating strength of concrete specimens, detecting defect initiation and progression in composite plates is presented. Additionally, an experimental verification of an …
-
Low-Resource Natural Language Understanding in Task-Oriented Dialogue
… performed by a Natural Language Understanding (NLU) component, which maps the text utterance into a semantic frame representation, involving two subtasks: intent classification (text classification) and slot filling (sequence tagging). Typically, new domains and languages are regularly added to …
-
Incidental Supervision for Natural Language Understanding
… annotations for natural language understanding (NLU) tasks is often labor-intensive and demands significant domain-specific expertise, making it crucial to obtain supervision from indirect signals to improve target task performance. This dissertation presents a novel approach for enhancing NLU by …
-
Utilisation des caractéristiques prosodiques pour optimiser un système de compréhension du langage naturel
… -Le système de compréhension du langage naturel (NLU); -Le système de dialogue ou agent conversationnel (CA). Dans cette architecture, les sorties des composants précédents servent d’entrées aux composants suivants. Les caractéristiques du signal acoustique ne font pas partie de la sortie du …
-
Evaluating and Enhancing Large Language Models (LLMs) in the Clinical Domain
… certain unseen natural language understanding (NLU) tasks; and (3) as LLMs are typically trained on vast amounts of data, there is a substantial risk of data contamination, where evaluation benchmarks unintentionally overlap with training data, leading to inflated test performance and …
-
A New Comprehensive and Practical Taxonomy of Demands Healthcare Professionals Experience: The Development Process and Testing Using Machine Learning
… IBM Watson’s Natural Language Understanding (NLU) service, were used to replicate human coding. IBM Watson’s NLU service demonstrated a high level of accuracy replicating comments in the superordinate (i.e., large) and basic (i.e., medium) levels of the TDHPE but demonstrated a low level of …
-
Modelos Neurais Auto-organizados em Interação Humano-Robô por Fala
… e compreensão auto-organizada de fala (SAoIHR-NLU) para operações em sistemas robóticos. No módulo SAoIHR-ASR ocorre o reconhecimento de palavras isoladas ou fala contínua em ambientes perturbados e com muitas variações na fala dos locutores. Já o módulo SAoIHR-NLU realiza a compreensão de …
-
Using ChatGPT to Augment Software Engineering Chatbots Datasets
… chatbot is a Natural Language Understanding (NLU) component that enables the chatbots to comprehend the user's queries. However, the NLU requires extensive, high-quality training data (examples) to accurately interpret user queries. Prior work shows that the creation and augmentation of SE …
-
Improving Natural Language Understanding via Contrastive Learning Methods
<p>Natural language understanding (NLU) is an essential but challenging task in Natural Language Processing (NLP), aiming to automatically extract and understand the semantic information from raw text or voice data. Among the previous NLU solutions, representation learning methods have recently …
-
Self-Determination Theory and Faculty Behavior: A Quantitative Study of Faculty Leaders' Use of Assessment Evidence
… a single institution, National Louis University (NLU). Results indicated a significant and positive relationship suggesting an increase in meeting the collective SDT needs would be met with an increase in faculty program leaders use of assessment evidence. Implications for further research are …
-
Spoken Language Understanding: Deep Neural Network Approaches for Low-Resource Languages
… processed by a natural language understanding (NLU) module. While effective, these systems face significant challenges in low-resource scenarios, where an ASR system may be unavailable or produce low-quality transcripts, propagating the errors to the NLU module. Moreover, separate training of …
-
Design and Implementation of a Memory Efficient Hardware Accelerator for Online Learning in Neuromorphic Systems
… hardware accelerator for online learning (NLU) was developed. NLU can be integrated into a multi-core system, such as SpiNNaker, to enhance the training process. A chip was fabricated, and the design was validated in silicon. It was shown that NLU could accelerate the e-prop algorithm for …
-
Anaphora in natural language understanding : a survey
… computer-based natural language understanding (NLU) systems encounter is that of linguistic reference, and in particular anaphora (abbreviated reference). For example, in a text as simple as: Nadia showed sue her new car. orange. The seats were Day-Glo knowing that "her" probably means Nadia and …
-
Enhancing Intent Classification via Zero-shot and Few-shot ChatGPT Prompting Engineering: Generating training data or directly detecting intents?
… Φυσικής Γλώσσας (Natural Language Understanding, NLU). Μεταξύ άλλων, τα Παραγωγικά LLMs έχουν επιδείξει την ικανότητά τους στην παραγωγή φράσεων χρήστη (user utterances) για συγκεκριμένες προθέσεις (intents), οι οποίες φράσεις μπορούν να αξιοποιηθούν για την εκπαίδευση NLU μοντέλων. Στην πράξη, …
-
Nonlinear ultrasound for radiation damage detection
… damage in RPV steels. Nonlinear ultrasound (NLU) is a nondestructive evaluation technique that is sensitive to microstructural features such as dislocations, precipitates, and their interactions in metallic materials. The physical effect monitored by NLU is the generation of higher harmonic …
-
Investigation of classical and nonclassical nonlinearity in metals
Nonlinear ultrasound (NLU) techniques such as second harmonic generation (SHG) and nonlinear resonant ultrasound spectroscopy (NRUS) have shown promise in detecting microstructural damage in materials before macroscopic failure can occur. However, before these methods can be implemented in the …
Page 1 of 9