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 10 of 10 for “"pretrained transformers"”.
-
Pretrained Transformers for Efficient and Robust Information Retrieval
Pretrained transformers have significantly advanced the field of information retrieval (IR) since the introduction of BERT. Through unsupervised pretraining followed by task-aware finetuning, the encoder-only BERT effectively captures the complex semantics of texts and overcomes the limitations of …
-
Self-supervised text sentiment transfer with rationale predictions and pretrained transformers
… identification method. We also experiment with a pretrained encoder-decoder Transformer model, known as BART, as a method for improving upon previous sentiment transfer results. This pretrained model is fine-tuned first in an unsupervised manner as a denoising autoencoder to reconstruct sentences …
-
Future Sight: Dynamic Story Generation with Large Pretrained Language Models
… inference. We build an interactive system using pretrained transformers finetuned on a novel objective to temporally interpolate between a story context c and a future plot event f. At inference time, users can suggest future plot events along with a distance, in sentences, to coerce a …
-
Improving Relation Extraction from Unstructured Genealogical Texts Using Fine-Tuned Transformers
… makes use of recently developed and massively pretrained transformers and fine-tuning techniques to take advantage of these deep neural models’ inherent understanding of English syntax and semantics for classification. With only a fraction of labeled data typically needed to train large models, …
-
SCALING PRE-TRAINING DATA & LANGUAGE MODELS FOR AFRICAN LANGUAGES
Recent advancements in language models, particularly for high-resource languages, have not been paralleled in low-resource languages spoken across Africa. This thesis addresses this gap by scaling pre-training data and developing improved language models for African languages. We introduce Wura, a …
-
Multilingual Financial Text Summarisation
… text in multiple languages. Using advanced pretrained transformers, our system can accurately identify and extract essential information from financial documents and generate extractive and abstractive summaries in various languages.
-
The power of adaptivity in multi-task representation learning
… Second, we consider multi-task learning with transformers in the setting of in-context learning (ICL). ICL entails solving a new task simply by running a forward pass on a prompt consisting of an instruction and examples of how to solve the task, with no model updates involved. Pretrained …
-
Development and Evaluation of Vision-Language Models for Ergonomic Physical Exposure Assessment in Occupational Manual Material Handling
Work-related musculoskeletal disorders remain a leading cause of lost workdays and substantial costs for workers and employers, and manual material handling (MMH) tasks are a major contributor to the physical exposures that drive this risk. Existing physical exposure assessment methods, including …
-
Democratizing and Modernizing Information Access: From Open Rerankers to Scalable RAG Evaluation
Modern information access increasingly relies on complex pipelines involving large language models (LLMs), fundamentally changing how users interact with information, from sophisticated multi-stage retrieval pipelines to end-to-end retrieval-augmented generation (RAG) systems. While these …
-
Benchmarks, Data, and Evaluation for Robust Retrieval and Retrieval-Augmented Generation on Heterogeneous Domains and Languages
… a retrieval system. Similarly, with the onset of pretrained transformers, retrieval systems have demonstrated strong downstream accuracy in the in-domain setting. However, their robustness in the zero-shot scenario remains limited, suggesting that these assumptions do not consistently hold in …