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 15 of 15 for “"Limited Supervision"”.
-
Learning video representations with limited supervision
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms
-
Guided text summarization with limited supervision
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms
-
Towards Generalizable Information Extraction with Limited Supervision
… addressing information extraction (IE) under limited supervision. In this dissertation, we approach information extraction with limited supervision from three perspectives. Firstly, we refine the previous classification-based extraction paradigm by introducing a query-and-extract framework, …
-
Deep learning of visual features with limited supervision.
… methods for learning deep visual features with limited human supervision, expanding deep learning’s applicability to diverse real-world tasks. We propose solutions in three key areas. First, we introduce a selective pretraining approach that enhances transfer learning by selecting pre-training …
-
Multi-dimensional mining of unstructured data with limited supervision
… text data into multi-dimensional knowledge with limited supervision. We investigate two core questions: 1. How to identify task-relevant data with declarative queries in multiple dimensions? 2. How to distill knowledge from data in a multi-dimensional space? To address the above questions, we …
-
Formality Style Transfer Within and Across Languages with Limited Supervision
… examples of style transfer are only available in limited quantities. We first address this problem by inducing a lexical formality model based on word embeddings and a small number of representative formal and informal words. This enables us to assign sentential formality scores and rerank …
-
Learning-based Methods for Fault Detection in Fiber-Optic Networks: Monitoring under Domain Shifts and Limited Supervision
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Weakly supervised aspect extraction for domain-specific texts
… from the domain-specific raw texts with very limited supervision – only a few user-provided seed words per each aspect. Specifically, our proposed neural model is equipped with multi-head attention and self-training. The multi-head attention is learned from the seed words to ensure that the …
-
Weakly-supervised text classification
… to deep neural models and meanwhile support limited supervision types. In this work, we propose a weakly-supervised framework that addresses the lack of training data in neural text classification. Our framework consists of two modules: (1) a pseudo-document generator that leverages seed …
-
Neural Sequence Modeling for Domain-Specific Language Processing: A Systematic Approach
… from domain knowledge and 3) learning under limited supervision. Our work can also potentially benefit more domains with large amounts of sequential data.
-
Probabilistic models for multi-view semi-supervised learning and coding
… accurate classification models in the face of limited supervision and to cope with the relatively large amount of potentially redundant information transmitted by each sensor or modality (i.e., view). We investigate and develop novel multi view learning algorithms capable of learning from …
-
Program Evaluation: Metacognition in a Blended Learning Environment
… at an early age, not enroll in college, and have limited opportunities in regards to employment. Instead of developing systems to address these needs, many American schools have chosen to label these students as at-risk and place them in computer labs with limited supervision. Considering the …
-
The law and the beautiful: a critical analysis of how Kenyan Law addresses appearance discrimination
… dress codes and grooming practices, under limited supervision. These dress codes and grooming practices seem fair and inobtrusive at face value, however, they have created a habitable environment for the proliferation of appearance discrimination. Appearance discrimination is particularly …
-
Interpreting Deep Neural Networks and Beyond: Visualization, Learning Dynamics, and Disentanglement
… Experimental results show that using very limited supervision significantly improves disentanglement quality and that the proposed method can generalize well to unseen images in the tasks of semantic fine-grained image editing. Looking forward, with more efforts and meaningful interactions …
-
Advanced Radar Sounder Data Analysis Methods under Limited labeled Data Constraints
… methods that can operate effectively under weak supervision and limited labeled data, while also generalizing across different environments. This thesis addresses these challenges through a progression of frameworks that advance from classical deep learning to foundation models, with an emphasis …