Search
Skip to Search Results- 2Abdi Oskouie, Mina
- 2Birkbeck, Neil Aylon Charles
- 2Cai, Zhipeng
- 2Chen, Jiyang
- 2Chowdhury, Md Solimul
- 2Chubak, Pirooz
- 74Machine Learning
- 70Reinforcement Learning
- 41Artificial Intelligence
- 36Machine learning
- 22Natural Language Processing
- 22Reinforcement learning
-
Probing the Robustness of Pre-trained Language Models for Structured and Unstructured Entity Matching
DownloadSpring 2023
The paradigm of fine-tuning Pre-trained Language Models (PLMs) has been successful in Entity Matching (EM). Many contemporary works leverage PLM-based models to push the state of the results. However, using the power of transformer-based models has some downsides in this task. Despite their...
-
Fall 2023
Product Entity Matching (PEM) is a challenging subfield of record linkage that involves linking records referring to the same real-world product. Despite recent transformer models showing near-perfect performance scores on various datasets, they struggle the most when dealing with PEM datasets....
-
Fall 2009
This thesis addresses the challenge of prognosis, in terms of survival prediction, for patients with Glioblastoma Multiforme brain tumors. Glioblastoma is the most malignant brain tumor, which has a median survival time of no more than a year. Accurate assessment of prognostic factors is critical...
-
Fall 2018
Heterogeneous computing is becoming increasingly common in high-end computer systems, with vendors often including compute accelerators such as Graphics Processing Units~(GPUs) and Field-Programmable Gate Arrays~(FPGAs) for increased throughput and power efficiency. This thesis addresses the...
-
Spring 2023
Recent advancements in large language models and program synthesis have enabled the development of powerful programming assistance tools. These tools are designed to help the programmer while writing a program in an online setting. In this thesis we introduce a programming assistant that can...
-
Spring 2023
Cost-guided bottom-up search (BUS) algorithms use a cost function to guide the search for solving program synthesis tasks. In this thesis, we show that current state-of-the-art cost-guided BUS algorithms suffer from a common problem: they can lose useful information given by the model and fail to...
-
Spring 2024
Text attribute transfer (TAT) is a natural language processing task that involves transforming some attributes of a given text while preserving other attributes. Recently, prompting approaches have been explored in TAT with the emergence of various pretrained language models (PLMs), where a...