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 18 of 18 for “"SBERT"”.
-
Deep Learning for Intertext Discovery in Latin Epic: Latin SBERT and the Lucan-Vergil Benchmark
… methods: the Latin BERT approaches and the Latin SBERT approaches. Chapter 3 compares and contrasts how Saussurean signs and deconstruction affect literary theory and natural language processing practices. Chapter 4 studies some of the winning Latin SBERT results in fine detail in order to glean …
-
Exploring sentence embeddings for better argument relation classification
… embedding models—InferSent, Sent2Vec, and SBERT—on text classification tasks. Our findings show that SBERT performs best, underscoring the importance of Transformer-based architectures in capturing sentence semantics. However, as SBERT relies on annotated data, we explore self-supervised …
-
Vyhledávání kurzů na základě podobnosti
… kurzů byly využity vektorové modely TF-IDF a SBERT, na které byly aplikovány aproximační algoritmy pro vyhledávání k-nejbližších sousedů. Součástí řešení je webová aplikace s REST API a uživatelským rozhraním, která umožňuje efektivní vyhledávání podobných kurzů. Výsledky testování ukazují, že …
-
Modelo exploratorio no supervisado para el análisis semántico del comportamiento económico a partir de fuentes oficiales de difusión audiovisual, mediante técnicas de NLP y Clustering
… semánticas como TF-IDF, Word2Vec y BERT/SBERT. Las noticas fueron clasificadas en categorías económicas y análisis de sentimiento, posteriormente se aplica una reducción de dimensionalidad mediante el Análisis de Componentes Principales (PCA) y algoritmos de clustering (K-Means, DBSCAN y …
-
Depression detection in social media via differential text embedding
… depression symptoms. We then used SBERT embedding vectors to measure the similarities between different tweets and anchor points as a distance in the vector space, or fed them directly into the machine learning model. We assessed the capability of our approach on two different …
-
Systém doporučování diplomových prací
… přirozeného jazyka (NLP): TF-IDF, BERT, SBERT, ALBERT, DistilBERT, RoBERTa a XLNet. Byl použit doporučovací systém typu content-based. Testování bylo provedeno za účasti studentů, kteří si již vybrali svou diplomovou práci a kteří vědí, která slova nejlépe vystihují jejich práci. …
-
Generating Adversarial Malware Examples Using Particle Swarm Optimization
… using the state-of-art Sentence Transformers (SBERT) to generate API mapping. Additionally, we categorize the mapping into four categories, making the attacks more practicability, and then manually verify the substitution in practice, resulting in two mappings: Simple Replacement and Complete …
-
Počítač jako inteligentní spoluhráč ve slovně-asociační hře Krycí jména
… potřebných k vítězství. Naopak testování modelu SBERT ukázalo, že pro specifické potřeby hry Krycí jména nepřináší oproti modelu FastText žádné zlepšení.
-
Content-Based Course Recommendation
… similarity, I compare two embedding models, sBERT and OpenAI embeddings, and evaluate them by examining their similarity matrices and observing how subjects naturally cluster together. Based on these results, sBERT was selected for the final system due to its strong performance and ability to …
-
Detekce anomálií v textových datech
… Document Frequency (TF-IDF) a Sentence-BERT (SBERT) v kombinaci s metodami Isolation Forest, One-Class Support Vector Machine (One-Class SVM) a Local Outlier Factor (LOF). Vyhodnocení na SMS a e-mailových zprávách ukázalo, že detekce spamu jako anomálie je obtížnější u krátkých zpráv než u …
-
Pharmaceutical assay search with AI
… TF-IDF model and the Transformer models BERT, SBERT, and Longformer were used to get embeddings of protocol documents from a corpus of historical protocols. Their performance in retrieving relevant historical protocols was evaluated based on key technical criteria, where the TF-IDF models and …
-
Cognitive Map Generation for Vision and Language Navigation
… leveraging semantic similarity computed via SBERT. This two-stage process ensures temporal coherence and semantic grounding between text-based instructions and real-world visual environments. Experiments conducted on the Touchdown and Map2Seq datasets demonstrate improved navigation accuracy, …
-
Computational Representation, Analysis and Verification of Requirements in Engineering Design and Systems Engineering
… learning (ML), and graph theory. We develop Req-sBERT, a fine-tuned Sentence-BERT model, to generate embeddings that estimate semantic similarity between any pair of requirements. These embeddings facilitate detecting the evolution of requirements and documenting them using hierarchical trees. We …
-
Comparing PSO-Based Clustering Over Contextual Vector Embeddings to Modern Topic Modeling
… a general-purpose pre-trained language model (sBERT). A modified PSO algorithm (pPSO) that tracks particle fitness on a dimension-by-dimension basis is then applied to these embeddings to create clusters of related documents. The proposed methodology is demonstrated on three datasets across …
-
Mining from the Lens of Ecological Law: Obstacles and Opportunities for Re-formation
Ecological law is a legal paradigm that is emerging in response to the current ecological crisis. This thesis explores the main challenges and opportunities in existing laws, particularly in the context of mining, for a shift to this new paradigm. A synthesis of the main critiques, scientific and …
-
Bridging AI readiness and application: Prototyping a strategy-aligned language model for quality insights at Skanska. A comprehensive study of organizational AI maturity, applied NLP development, and scalable implementation in construction quality management
… a fine-tuned transformer classi fier (XLM-R and SBERT). Two promising category types, incident type and affected building component, were identified and co-developed with domain experts to struc ture the data. The results show that while AI readiness is moderate, initiatives often remain siloed …
-
Investigação da influência da experiência subjetiva com o jogo eletrônico no sono, sonhos, pesadelos e incubação onírica subsequentes
… for dream influence. Semantic analysis via SBERT confirmed a closer proximity between dream reports and game descriptions in participants with high incubation. Our findings indicate that the experience with electronic games significantly affects dream content and recall, but not sleep …
-
Machine learning and neural methods for federated patent search
… BM25, semantic signals utilizing Sentence-BERT (SBERT) embeddings to capture deep conceptual context, and structural signals modeling the explicit relationships and importance weights between different document sections. A key innovation is the introduction of a query-adaptive weighting mechanism …