Using LLMs for the Extraction and Normalization of Product Attribute Values

arXiv:2403.02130v1 Announce Type: new
Abstract: Product offers on e-commerce websites often consist of a textual product title and a textual product description. In order to provide features such as faceted product filtering or content-based product recommendation, the websites need to extract attribute-value pairs from the unstructured product descriptions. This paper explores the potential of using large language models (LLMs), such as OpenAI's GPT-3.5 and GPT-4, to extract and normalize attribute values from product titles and product descriptions. For our experiments, …

abstract arxiv commerce cs.cl e-commerce extract extraction features filtering llms normalization product product recommendation recommendation textual type unstructured value values websites