Year: 2023
Type: dissertation
Abstract: Agriculture plays a crucial role in numerous households across Sub-Saharan Africa. \nDeveloping a question answering system that utilizes agricultural expertise and agroinformation can effectively bridge the support gap for farmers in the local community. \nMost advances in question answering research involve large language models trained on \nextensive data. Nevertheless, the conventional approach of fine-tuning has demonstrated \na significant decline in performance when models are fine-tuned on a small amount of \ndata. This decline is primarily attributed to the disparities between the objectives of pretraining and fine-tuning. One proposed alternative is to utilize prompt-based fine-tuning, \nwhich permits the model to be fine-tuned with only a few examples. Extensive research \nhas been done on the application of these methods to tasks such as text classification \nand not question answering. This research aims to study the feasibility of recent fewshot learning approaches, such as FewshotQA and Null prompting, for domain-specific \nagricultural data in 4 South African languages. We evaluated the overall performance \nof these approaches and investigated the effects of adapting these approaches for crosslingual extractive question answering of domain-specific data. The results obtained in \nthis study have shown valuable insight into the applicability of these methods to domainspecific data. These results have shown that these methods are capable of adequately \ncapturing the textual information of domain-specific data from the initial subset of data \npoints. Thus, there is potential for using these methods as a practical solution for limited \ndata.
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7000490410