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 24 for “"Semantic Understanding"”.
-
Knowledge engineering for semantic understanding
This thesis addresses the challenges of improving semantic understanding in conversational agents by combining Knowledge Graphs (KGs) and Large Language Models (LLMs) within a flexible, multi-domain knowledge plugin architecture. We explore the inherent difficulties LLMs face in interpreting …
-
Semantic understanding and commonsense reasoning in an adaptive photo agent
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2002.
-
Context-based multimedia semantics modelling and representation
… decisions. Existing methods for multimedia semantic understanding are limited to the computable low-level features; which raises the question of how to identify and represent the high-level semantic knowledge in multimedia resources.In order to bridge the semantic gap between multimedia …
-
A semantics based computational model for word learning
… shown that children learn new words by forming semantic relationships with words they already know. Human tutors often implicitly use semantics to assess a tutee's word knowledge from partial and noisy data. In this thesis, I present a cognitively inspired model that uses word semantics …
-
Autonomous learning of action-word semantics in a humanoid robot
… symbols or classify speech are ineffective. The semantic information which language conveys must be grounded in the agent’s complete sensorimotor experience. Typically, patterns from visual, auditory, and proprioceptive data streams which share the same conceptual cause are fused together in an …
-
Color Invariant Skin Segmentation
… are based entirely on color and increasing more semantic understanding. The resulting system exhibits a dramatic improvement in performance for images in which color details are diminished. We have demonstrated the concept using the U-Net architecture, and experimental results show improvements …
-
ADAPTIVE FRAMEWORKS FOR KNOWLEDGE EXTRACTION IN HETEROGENEOUS DATA ENVIRONMENTS
… external knowledge bases to enhance semantic understanding. SHIFT modular architecture provides seamless adaptation to different data modalities and domain requirements. The framework’s adaptability is demonstrated through comprehensive applications across distinct domains, from legal …
-
Monitoring and designing built environments with computer vision
… direction. Secondly, motivated by the need for semantic understanding of scenes for progress monitoring, we explore means of encouraging the geometric regularity we expect to see in scenes of built environments in outputs of 2D semantic segmentation methods. Finally, we address practical …
-
A Neuro-Symbolic Reinforcement Learning Architecture: Integrating Perception, Reasoning, and Control
… have demonstrated promise in tasks re- quiring a semantic understanding that can often be missed by traditional deep learning techniques. By integrating symbolic reasoning with deep learning, neuro-symbolic architec- tures aim to be both interpretable and flexible. This thesis aims to apply …
-
Representation learning of natural language and its application to language understanding and generation
… encode rich information such as the syntax and semantics of the language into dense vectors. It facilitates the modeling, manipulation and analysis of natural language in computational linguistics. Existing algorithms utilize corpus statistics such as word co-occurrences to learn general-purpose …
-
Enabling Semantically Grounded, Long Horizon Planning and Execution for Autonomous Agents
… directly from their environment to develop an understanding of the world. They will need to maintain a semantic understanding of their environment, including the kinds of objects they observe and their relationships to each other. At the same time, they must be able to reason over diverse …
-
Enhancing Natural Language Inference through Multi-Agent Deliberation
… Natural Language Inference (NLI), a key task in semantic understanding. However, this thesis demonstrates that the benefits of collaboration are not guaranteed. The effectiveness of a multi-agent system is critically dependent on the architecture of its deliberation protocol and the richness of …
-
General-Purpose Task Guidance from Natural Language in Augmented Reality using Vision-Language Models
… machine learning models for text and image semantic understanding and object localization. We built a proof-of-concept system using our approach and tested its accuracy and usability in a user study. We found that all operators were able to generate clear guidance for tasks in an office …
-
Multimodal learning and language models for enhanced knowledge representations
… data by developing a novel weakly supervised semantic distillation framework. Leveraging the rich semantic understanding embedded in large language models along with negative sampling strategies, this framework significantly improves retrieval accuracy and generalizability, particularly for …
-
Energy efficient accelerators for autonomous navigation in miniaturized robots
… buildings, caves, etc. Robot perception (i.e., semantic and geometric understanding) is considered the computation bottleneck in autonomous navigation systems because of the high dimensionality of the problem. For example, multi-scale object detection is desired for robustness, which requires …
-
Towards Object-based SLAM
… to dense SLAM, and now there is a demand for semantic understanding of the environment beyond pure geometric understanding. This thesis delves into object-based SLAM where the map consists of a set of objects with their semantic categories recognized and their poses and shapes estimated. Such …
-
Label-Efficient Visual Understanding with Consistency Constraints
… at solving various visual recognition and understanding tasks, as long as a sufficiently large labeled dataset is available during the training time. However, the progress of these visual tasks is limited by the number of manual annotations. On the other hand, it is usually time-consuming …
-
TIGER: Testing and Improving Generated Code with LLMs
… that every generated function is derived from semantic understanding rather than replication or pattern-matching. A core innovation of this work is the integration of an iterative refinement loop, which introduces structured feedback into the code generation process. After producing an initial …
-
Semantic and spatio-temporal understanding for computer vision driven worker safety inspection and risk analysis
… This dissertation explores methods for automated semantic and spatio-temporal visual understanding of workers and equipment and how to use them to improve automatic safety inspections and risk analysis: (1) a new method is developed to improve the breadth and depth of vision-based safety …
-
API Utility Enhancement: From Traditional Software to Deep Learning Frameworks
… of navigating APIs that require a profound understanding of underlying principles, parameter configurations, and context-specific scenarios. Misuse of APIs can lead to degraded performance, prolonged debugging efforts, and critical application failures, posing risks across both traditional …
Page 1 of 2