Comparison of Transformer-based Architectures for Product Categorization
Document Type
Article
Publication Date
2023
Abstract
The fast & continuous evolution of e-commerce search engines globally has encouraged researchers & industry specialists alike to improve product categorization models to elevate user experience. Also, the revolutionary emergence of large language models has given us the opportunity to capture the complex relationships and dependencies found in large datasets that we were not able to discover with traditional techniques, and not to mention the multitude of other natural language understanding tasks it performs. In this paper, we aim to evaluate different transformer-based architectures on the Amazon Shopping Queries dataset to determine which architecture is well-suited for the task of product categorization within an e-commerce platform.
Recommended Citation
C. Mohamed and A. Hamdy, "Comparison of Transformer-based Architectures for Product Categorization," 2023 International Conference on Computer and Applications (ICCA), Cairo, Egypt, 2023, pp. 1-5, doi: 10.1109/ICCA59364.2023.10401734.