Year: 2023
Type: dissertation
Abstract: Recent advances in the development of extremely large, multi-purpose models have motivated computer scientists to explore methods for adapting them to more specific tasks. \nFine-tuning is the most widely used approach to this problem, in which a more general model is trained on a new dataset of labeled data for the new task. While fine-tuning mitigates the data availability problem and enables models trained on small labeled datasets to achieve state-of-the-art performance, it also exhibits some key disadvantages: inefficiency, resource-intensive computation and making the models less general. \nThis study investigates the use of learnable prompts, a parameter-efficient fine-tuning alternative, \nin spoken language understanding (SLU) tasks. To our knowledge, learnable prompts have not been previously applied to SLU, but have been tested on text-based natural language processing (NLP) tasks and computer vision tasks, achieving promising results. Therefore, we’ll be introducing our proposed approach, using learnable prompts in a SLU context, and analyse some experimental results on two different deep learning-based end-to-end SLU models.
Author: Ciapponi, Stefano
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Fondazione Bruno Kessler
OpenAlex ID: W6987977990